aiskillstore/marketplace / skills/23blocks-os/ai-maestro-code-graph-query
ai-maestro-code-graph-query
VerifiedPROACTIVELY query the code graph database to understand relationships and impact of changes. Use this skill WHEN READING any file to understand context, when searching for files, when exploring the codebase, or when you need to understand what depends on a component. This is your primary tool for understanding code structure and avoiding breaking changes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.3 KB |
| output.json | config | 7.0 KB |
| skill-report.json | config | 72.6 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-06T00:27:45.450Z",
"slug": "23blocks-os-ai-maestro-code-graph-query",
"source_url": "https://github.com/23blocks-OS/ai-maestro/tree/main/skills/graph-query",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "078d400a484219965a16ae3b74bf337743491c4d6be39eca85d1670a08093090",
"tree_hash": "8c4cfe67044a50a92bc5d9f93b368e2759349961d4e3991a1ea0dec26af624ae",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "ai-maestro-code-graph-query",
"description": "Query an AI Maestro code graph to inspect dependencies, callers, callees, associations, serializers, and related components before changing code.",
"summary": "Use AI Maestro graph queries to understand code relationships before editing.",
"icon": "📦",
"version": "1.0.0",
"author": "23blocks-OS",
"license": "MIT",
"tags": [
"code-analysis",
"dependency-graph",
"impact-analysis",
"refactoring",
"ai-maestro"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"filesystem",
"external_commands",
"network"
],
"category": "coding"
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "The skill provides useful AI Maestro code graph workflows, but it relies on Bash execution and strongly mandates automatic graph queries after reading files. The highest risks are unbundled PATH-resolved scripts, hidden home-directory installation under ~/.local/bin, and coercive prompt text that can push agents to execute commands without fresh user intent.",
"remediation": [
{
"issue": "Automatic Bash execution is mandated by prompt text.",
"suggestion": "Require explicit user confirmation before running graph scripts, especially after file reads or searches.",
"severity": "high"
},
{
"issue": "Graph scripts are not included in the reviewed skill package.",
"suggestion": "Bundle the scripts or pin their absolute paths and checksums so reviewers can verify executed code.",
"severity": "high"
},
{
"issue": "Installation targets ~/.local/bin and relies on PATH lookup.",
"suggestion": "Avoid hidden home-directory installs, or document the path clearly and verify script ownership before execution.",
"severity": "medium"
},
{
"issue": "The skill uses curl to contact a localhost service.",
"suggestion": "Disclose the local API dependency and avoid sending code content unless the user authorizes it.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "filesystem",
"evidence": [
{
"file": "output.json",
"line_start": 18,
"line_end": 18
},
{
"file": "output.json",
"line_start": 18,
"line_end": 18
},
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 141
},
{
"file": "SKILL.md",
"line_start": 159,
"line_end": 159
},
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 141
},
{
"file": "SKILL.md",
"line_start": 159,
"line_end": 159
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 40
},
{
"file": "SKILL.md",
"line_start": 40,
"line_end": 45
},
{
"file": "SKILL.md",
"line_start": 45,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 63
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 65
},
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 66
},
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 68
},
{
"file": "SKILL.md",
"line_start": 68,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 70
},
{
"file": "SKILL.md",
"line_start": 70,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 87
},
{
"file": "SKILL.md",
"line_start": 87,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 109
},
{
"file": "SKILL.md",
"line_start": 110,
"line_end": 110
},
{
"file": "SKILL.md",
"line_start": 111,
"line_end": 112
},
{
"file": "SKILL.md",
"line_start": 112,
"line_end": 126
},
{
"file": "SKILL.md",
"line_start": 126,
"line_end": 127
},
{
"file": "SKILL.md",
"line_start": 127,
"line_end": 128
},
{
"file": "SKILL.md",
"line_start": 128,
"line_end": 129
},
{
"file": "SKILL.md",
"line_start": 129,
"line_end": 130
},
{
"file": "SKILL.md",
"line_start": 130,
"line_end": 131
},
{
"file": "SKILL.md",
"line_start": 131,
"line_end": 132
},
{
"file": "SKILL.md",
"line_start": 132,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 133,
"line_end": 134
},
{
"file": "SKILL.md",
"line_start": 134,
"line_end": 139
},
{
"file": "SKILL.md",
"line_start": 139,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 141
},
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 142
},
{
"file": "SKILL.md",
"line_start": 142,
"line_end": 145
},
{
"file": "SKILL.md",
"line_start": 145,
"line_end": 155
},
{
"file": "SKILL.md",
"line_start": 155,
"line_end": 157
},
{
"file": "SKILL.md",
"line_start": 157,
"line_end": 159
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 145,
"line_end": 145
}
]
}
],
"static_findings": [
{
"id": "filesystem:output.json:18:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "output.json",
"line_start": 18,
"line_end": 18,
"snippet": "\"summary\": \"Prompt-based skill providing behavioral instructions. Executes local scripts from ~/.loc"
},
{
"id": "filesystem:output.json:18:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "output.json",
"line_start": 18,
"line_end": 18,
"snippet": "\"summary\": \"Prompt-based skill providing behavioral instructions. Executes local scripts from ~/.loc"
},
{
"id": "blocker:output.json:5:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "output.json",
"line_start": 5,
"line_end": 5,
"snippet": "\"summary\": \"Query code dependency graphs to understand relationships and avoid breaking changes\","
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": "Every time you use the `Read` tool on a code file, you MUST IMMEDIATELY query the graph to understan"
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 37,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 40,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 40,
"line_end": 45,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 45,
"line_end": 48,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 48,
"line_end": 52,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 63,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 63,
"line_end": 64,
"snippet": "| `graph-describe.sh <name>` | Describe a component or function |"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 64,
"line_end": 65,
"snippet": "| `graph-find-callers.sh <function>` | Find all functions that call this function |"
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 65,
"line_end": 66,
"snippet": "| `graph-find-callees.sh <function>` | Find all functions called by this function |"
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 66,
"line_end": 67,
"snippet": "| `graph-find-related.sh <component>` | Find related components (extends, includes, etc.) |"
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 67,
"line_end": 68,
"snippet": "| `graph-find-by-type.sh <type>` | Find all components of a type (model, controller, etc.) |"
},
{
"id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 68,
"line_end": 69,
"snippet": "| `graph-find-serializers.sh <model>` | Find serializers for a model |"
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 69,
"line_end": 70,
"snippet": "| `graph-find-associations.sh <model>` | Find model associations (belongs_to, has_many) |"
},
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 70,
"line_end": 75,
"snippet": "| `graph-find-path.sh <from> <to>` | Find call path between two functions |"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 75,
"line_end": 81,
"snippet": "| `graph-index-delta.sh [project-path]` | **Delta index** - only re-index changed files |"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 81,
"line_end": 87,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 87,
"line_end": 107,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 107,
"line_end": 107,
"snippet": "| Model | `graph-describe.sh`, `graph-find-serializers.sh`, `graph-find-associations.sh` |"
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 108,
"line_end": 108,
"snippet": "| Controller | `graph-describe.sh`, `graph-find-callees.sh` |"
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 109,
"line_end": 109,
"snippet": "| Service | `graph-describe.sh`, `graph-find-callers.sh` |"
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 110,
"line_end": 110,
"snippet": "| Function | `graph-find-callers.sh`, `graph-find-callees.sh` |"
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 111,
"line_end": 112,
"snippet": "| Serializer | `graph-describe.sh` |"
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 112,
"line_end": 126,
"snippet": "| Any class | `graph-find-related.sh` |"
},
{
"id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 126,
"line_end": 127,
"snippet": "Use with `graph-find-by-type.sh`:"
},
{
"id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 127,
"line_end": 128,
"snippet": "- `model` - Database models"
},
{
"id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 128,
"line_end": 129,
"snippet": "- `serializer` - JSON serializers"
},
{
"id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 129,
"line_end": 130,
"snippet": "- `controller` - API controllers"
},
{
"id": "external_commands:SKILL.md:130:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 130,
"line_end": 131,
"snippet": "- `service` - Service objects"
},
{
"id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 131,
"line_end": 132,
"snippet": "- `job` - Background jobs"
},
{
"id": "external_commands:SKILL.md:132:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 132,
"line_end": 133,
"snippet": "- `concern` - Shared modules"
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 133,
"line_end": 134,
"snippet": "- `component` - React/Vue components"
},
{
"id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 134,
"line_end": 139,
"snippet": "- `hook` - React hooks"
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 139,
"line_end": 140,
"snippet": "- Check PATH: `which graph-describe.sh`"
},
{
"id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 140,
"line_end": 141,
"snippet": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`"
},
{
"id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 141,
"line_end": 142,
"snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
},
{
"id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 142,
"line_end": 145,
"snippet": "- If not found, run: `./install-graph-tools.sh`"
},
{
"id": "external_commands:SKILL.md:145:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 145,
"line_end": 155,
"snippet": "- Ensure AI Maestro is running: `curl http://localhost:23000/api/agents`"
},
{
"id": "external_commands:SKILL.md:155:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 155,
"line_end": 157,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 157,
"line_end": 159,
"snippet": "```"
},
{
"id": "network:SKILL.md:145:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 145,
"line_end": 145,
"snippet": "- Ensure AI Maestro is running: `curl http://localhost:23000/api/agents`"
},
{
"id": "filesystem:SKILL.md:140:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 140,
"line_end": 140,
"snippet": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`"
},
{
"id": "filesystem:SKILL.md:141:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 141,
"line_end": 141,
"snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
},
{
"id": "filesystem:SKILL.md:159:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 159,
"line_end": 159,
"snippet": "This installs scripts to `~/.local/bin/`."
},
{
"id": "filesystem:SKILL.md:140:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 140,
"line_end": 140,
"snippet": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`"
},
{
"id": "filesystem:SKILL.md:141:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 141,
"line_end": 141,
"snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
},
{
"id": "filesystem:SKILL.md:159:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 159,
"line_end": 159,
"snippet": "This installs scripts to `~/.local/bin/`."
}
],
"finding_verdicts": [
{
"id": "filesystem:output.json:18:hidden-file-in-home-directory",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "The hidden home path appears inside a JSON report summary string, not executable skill instructions. The actual hidden-directory behavior is evaluated in SKILL.md findings."
},
{
"id": "filesystem:output.json:18:hidden-file-access",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "This is a non-executable JSON summary that mentions ~/.local/bin. It does not read or write hidden files by itself."
},
{
"id": "blocker:output.json:5:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The text describes code dependency graph analysis, not host or network reconnaissance. No system inventory behavior is present at this location."
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticks wrap the word Read as Markdown tool formatting. The line is coercive prompt text, but this specific static shell-execution pattern is not present."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.86,
"reason": "This block is a numbered workflow description rather than a shell command. The automatic behavior is addressed as a semantic finding."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks here are Markdown formatting, not Ruby execution or a shell invocation. No executable command appears at this finding location."
},
{
"id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "This command is part of the skill workflow for graph lookup and is intended to be run by the agent. It is legitimate functionality but still represents local command execution risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks here are Markdown formatting, not Ruby execution or a shell invocation. No executable command appears at this finding location."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "This command is part of the skill workflow for graph lookup and is intended to be run by the agent. It is legitimate functionality but still represents local command execution risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks here are Markdown formatting, not Ruby execution or a shell invocation. No executable command appears at this finding location."
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "The skill documents a delta indexing script that can process project paths. This is local command execution over repository content and should require user awareness.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "The code block explicitly instructs running graph-index-delta.sh, optionally with a project path. This is intended Bash execution over local files.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks here are Markdown formatting, not Ruby execution or a shell invocation. No executable command appears at this finding location."
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.62,
"reason": "This line references graph-find-by-type.sh as a command users should run with selected type values. It is lower-risk documentation but still part of Bash-driven workflow.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:130:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:132:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The backticked word is a type argument, not a shell command. It does not by itself invoke external execution."
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The troubleshooting step asks the agent or user to run which against a graph script. The command is low impact but confirms local shell execution is part of the skill.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "The line instructs listing ~/.local/bin graph scripts. This reads a hidden home directory and supports execution of locally installed scripts.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "This line contains a path formatted in Markdown, not a shell command. The hidden-directory risk is covered by filesystem findings."
},
{
"id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.84,
"reason": "The skill tells users to run ./install-graph-tools.sh if commands are missing. The installer is not included in the scanned files, so running it is unreviewed local code execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:145:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.8,
"reason": "The skill instructs running curl against a local API endpoint. This is a network-capable command and interacts with a local service outside the skill files.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:155:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "This code block contains the install-graph-tools.sh command. Running an installer that is not present in the reviewed files is local execution risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "This is the closing Markdown fence for the install example. The executable installer risk is captured by the preceding finding."
},
{
"id": "network:SKILL.md:145:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The URL is limited to localhost, so there is no evidence of external exfiltration. It still directs a network request to a local service and should be disclosed.",
"severity": "low"
},
{
"id": "filesystem:SKILL.md:140:hidden-file-in-home-directory",
"verdict": "confirmed",
"confidence": 0.76,
"reason": "The skill instructs accessing ~/.local/bin, a hidden home-directory path outside the project. This creates review and PATH-trust risk for scripts the agent may execute.",
"severity": "high"
},
{
"id": "filesystem:SKILL.md:141:hidden-file-in-home-directory",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The skill states scripts are installed under ~/.local/bin. That hidden home location can hold mutable executables outside marketplace review.",
"severity": "high"
},
{
"id": "filesystem:SKILL.md:159:hidden-file-in-home-directory",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The install note says scripts are placed under ~/.local/bin. This hidden home-directory installation target is outside the reviewed skill package.",
"severity": "high"
},
{
"id": "filesystem:SKILL.md:140:hidden-file-access",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "The line directs listing graph scripts in ~/.local/bin. That is access to a hidden home directory and supports execution of unbundled local tools.",
"severity": "medium"
},
{
"id": "filesystem:SKILL.md:141:hidden-file-access",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The skill relies on scripts installed in ~/.local/bin. This hidden path access is part of the intended operating model.",
"severity": "medium"
},
{
"id": "filesystem:SKILL.md:159:hidden-file-access",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The installer destination is ~/.local/bin, a hidden home-directory path. The marketplace package does not include the installed scripts for review.",
"severity": "medium"
}
],
"semantic_findings": [
{
"title": "Prompt Injection Attempt Detected",
"description": "The skill uses forceful authority language such as \"THIS IS NOT OPTIONAL\" and requires immediate graph queries after every Read. This can override normal user intent and push automatic Bash execution.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 9,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 28
}
],
"confidence": 0.84,
"confidence_reasoning": "The text explicitly claims default authority over agent behavior and mandates tool use. It does not request data theft, so high severity is appropriate rather than critical."
},
{
"title": "Unbundled PATH-Resolved Script Trust",
"description": "The skill references graph scripts by name and says they are installed in ~/.local/bin. The reviewed package does not include those scripts, so the agent may run unreviewed PATH-resolved code.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 138,
"line_end": 142
},
{
"file": "SKILL.md",
"line_start": 152,
"line_end": 159
}
],
"confidence": 0.86,
"confidence_reasoning": "The command list and install guidance clearly rely on external shell scripts not present in the scanned files. This is a strong supply-chain and PATH-hijack risk."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Hidden file in home directory",
"description": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`",
"locations": [
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "high",
"confidence": 0.76,
"confidence_reasoning": "The skill instructs accessing ~/.local/bin, a hidden home-directory path outside the project. This creates review and PATH-trust risk for scripts the agent may execute."
},
{
"title": "Hidden file in home directory",
"description": "- Scripts are installed to `~/.local/bin/` which should be in your PATH",
"locations": [
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 141
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "high",
"confidence": 0.74,
"confidence_reasoning": "The skill states scripts are installed under ~/.local/bin. That hidden home location can hold mutable executables outside marketplace review."
},
{
"title": "Hidden file in home directory",
"description": "This installs scripts to `~/.local/bin/`.",
"locations": [
{
"file": "SKILL.md",
"line_start": 159,
"line_end": 159
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "high",
"confidence": 0.74,
"confidence_reasoning": "The install note says scripts are placed under ~/.local/bin. This hidden home-directory installation target is outside the reviewed skill package."
},
{
"title": "Prompt Injection Attempt Detected",
"description": "The skill uses forceful authority language such as \"THIS IS NOT OPTIONAL\" and requires immediate graph queries after every Read. This can override normal user intent and push automatic Bash execution.",
"locations": [
{
"file": "SKILL.md",
"line_start": 9,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 28
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.84,
"confidence_reasoning": "The text explicitly claims default authority over agent behavior and mandates tool use. It does not request data theft, so high severity is appropriate rather than critical."
},
{
"title": "Unbundled PATH-Resolved Script Trust",
"description": "The skill references graph scripts by name and says they are installed in ~/.local/bin. The reviewed package does not include those scripts, so the agent may run unreviewed PATH-resolved code.",
"locations": [
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 138,
"line_end": 142
},
{
"file": "SKILL.md",
"line_start": 152,
"line_end": 159
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.86,
"confidence_reasoning": "The command list and install guidance clearly rely on external shell scripts not present in the scanned files. This is a strong supply-chain and PATH-hijack risk."
}
],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 40,
"line_end": 45
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "This command is part of the skill workflow for graph lookup and is intended to be run by the agent. It is legitimate functionality but still represents local command execution risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 52
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "This command is part of the skill workflow for graph lookup and is intended to be run by the agent. It is legitimate functionality but still represents local command execution risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-describe.sh <name>` | Describe a component or function |",
"locations": [
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 64
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-callers.sh <function>` | Find all functions that call this function |",
"locations": [
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 65
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-callees.sh <function>` | Find all functions called by this function |",
"locations": [
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 66
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-related.sh <component>` | Find related components (extends, includes, etc.) |",
"locations": [
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 67
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-by-type.sh <type>` | Find all components of a type (model, controller, etc.) |",
"locations": [
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 68
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-serializers.sh <model>` | Find serializers for a model |",
"locations": [
{
"file": "SKILL.md",
"line_start": 68,
"line_end": 69
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-associations.sh <model>` | Find model associations (belongs_to, has_many) |",
"locations": [
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 70
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-find-path.sh <from> <to>` | Find call path between two functions |",
"locations": [
{
"file": "SKILL.md",
"line_start": 70,
"line_end": 75
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `graph-index-delta.sh [project-path]` | **Delta index** - only re-index changed files |",
"locations": [
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 81
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "The skill documents a delta indexing script that can process project paths. This is local command execution over repository content and should require user awareness."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 87
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The code block explicitly instructs running graph-index-delta.sh, optionally with a project path. This is intended Bash execution over local files."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Model | `graph-describe.sh`, `graph-find-serializers.sh`, `graph-find-associations.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 107
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Controller | `graph-describe.sh`, `graph-find-callees.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 108
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Service | `graph-describe.sh`, `graph-find-callers.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 109
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Function | `graph-find-callers.sh`, `graph-find-callees.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 110,
"line_end": 110
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Serializer | `graph-describe.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 111,
"line_end": 112
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| Any class | `graph-find-related.sh` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 112,
"line_end": 126
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line documents a graph command that the skill later tells agents to run automatically. Because the command is PATH-resolved, it carries local execution and trust-boundary risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "Use with `graph-find-by-type.sh`:",
"locations": [
{
"file": "SKILL.md",
"line_start": 126,
"line_end": 127
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.62,
"confidence_reasoning": "This line references graph-find-by-type.sh as a command users should run with selected type values. It is lower-risk documentation but still part of Bash-driven workflow."
},
{
"title": "Ruby/shell backtick execution",
"description": "- Check PATH: `which graph-describe.sh`",
"locations": [
{
"file": "SKILL.md",
"line_start": 139,
"line_end": 140
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The troubleshooting step asks the agent or user to run which against a graph script. The command is low impact but confirms local shell execution is part of the skill."
},
{
"title": "Ruby/shell backtick execution",
"description": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`",
"locations": [
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 141
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The line instructs listing ~/.local/bin graph scripts. This reads a hidden home directory and supports execution of locally installed scripts."
},
{
"title": "Ruby/shell backtick execution",
"description": "- If not found, run: `./install-graph-tools.sh`",
"locations": [
{
"file": "SKILL.md",
"line_start": 142,
"line_end": 145
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.84,
"confidence_reasoning": "The skill tells users to run ./install-graph-tools.sh if commands are missing. The installer is not included in the scanned files, so running it is unreviewed local code execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "- Ensure AI Maestro is running: `curl http://localhost:23000/api/agents`",
"locations": [
{
"file": "SKILL.md",
"line_start": 145,
"line_end": 155
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.8,
"confidence_reasoning": "The skill instructs running curl against a local API endpoint. This is a network-capable command and interacts with a local service outside the skill files."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 155,
"line_end": 157
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "This code block contains the install-graph-tools.sh command. Running an installer that is not present in the reviewed files is local execution risk."
},
{
"title": "Hidden file access",
"description": "- Verify scripts installed: `ls -la ~/.local/bin/graph-*.sh`",
"locations": [
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "The line directs listing graph scripts in ~/.local/bin. That is access to a hidden home directory and supports execution of unbundled local tools."
},
{
"title": "Hidden file access",
"description": "- Scripts are installed to `~/.local/bin/` which should be in your PATH",
"locations": [
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 141
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The skill relies on scripts installed in ~/.local/bin. This hidden path access is part of the intended operating model."
},
{
"title": "Hidden file access",
"description": "This installs scripts to `~/.local/bin/`.",
"locations": [
{
"file": "SKILL.md",
"line_start": 159,
"line_end": 159
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The installer destination is ~/.local/bin, a hidden home-directory path. The marketplace package does not include the installed scripts for review."
}
],
"low_findings": [
{
"title": "Hardcoded URL",
"description": "- Ensure AI Maestro is running: `curl http://localhost:23000/api/agents`",
"locations": [
{
"file": "SKILL.md",
"line_start": 145,
"line_end": 145
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.72,
"confidence_reasoning": "The URL is limited to localhost, so there is no evidence of external exfiltration. It still directs a network request to a local service and should be disclosed."
}
],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 329,
"audit_model": "codex",
"audited_at": "2026-07-06T00:27:45.450Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Analyze Code Graph Dependencies",
"value_statement": "Changing code without dependency context can break callers, serializers, and related components. This skill uses AI Maestro graph commands to inspect relationships before edits.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"AI Maestro",
"code graph query",
"dependency analysis",
"call graph",
"impact analysis",
"refactoring safety",
"codebase navigation"
],
"actual_capabilities": [
"Describe code components or functions through AI Maestro graph queries.",
"Find callers and callees for a function before changes.",
"Find serializers and model associations for data model updates.",
"Find related classes, modules, and components by relationship type.",
"Trace call paths between two named functions.",
"Run delta indexing to refresh changed project files."
],
"limitations": [
"Requires AI Maestro and its local API to be running on the workstation.",
"Requires graph scripts to be installed and available on PATH.",
"Requires an indexed project before queries return useful results.",
"Uses Bash commands, so users should review commands before execution."
],
"use_cases": [
{
"title": "Review Model Change Impact",
"description": "Find serializers, associations, and dependent code before changing a model.",
"target_user": "Backend developers"
},
{
"title": "Prepare Safer Refactors",
"description": "Identify callers and callees before changing a function signature or moving logic.",
"target_user": "Feature engineers"
},
{
"title": "Explore Unknown Codebases",
"description": "Map relationships between controllers, services, jobs, and components during onboarding.",
"target_user": "Codebase maintainers"
}
],
"prompt_templates": [
{
"title": "Inspect One Component",
"scenario": "Beginner dependency lookup",
"prompt": "Use the code graph to describe this component. Summarize what it depends on and what depends on it."
},
{
"title": "Check Function Impact",
"scenario": "Before changing a function",
"prompt": "Find callers and callees for this function. Explain which callers need review before I edit it."
},
{
"title": "Review Model Dependencies",
"scenario": "Before changing a data model",
"prompt": "Find serializers, associations, and related components for this model. Highlight any risky downstream dependencies."
},
{
"title": "Trace Cross-Layer Flow",
"scenario": "Advanced architecture analysis",
"prompt": "Trace the call path between this entry point and this internal function. Explain the main layers and change risks."
}
],
"output_examples": [
{
"input": "Find the impact of changing the payment processing function.",
"output": [
"The function is called by checkout, subscription renewal, and refund workflows.",
"It calls validation, card charging, and transaction logging logic.",
"Review checkout and renewal tests before changing the function signature."
]
},
{
"input": "Check dependencies for the user model before adding a field.",
"output": [
"The model has serializers for public profile and admin views.",
"It is associated with accounts, sessions, orders, and audit records.",
"Update serializer coverage and migration tests before exposing the new field."
]
}
],
"best_practices": [
"Confirm graph commands with the user before running Bash in a repository.",
"Refresh the graph index after meaningful code changes.",
"Compare graph results with tests before making high-impact refactors."
],
"anti_patterns": [
"Running PATH-resolved graph scripts without checking their source.",
"Treating graph output as complete when the index may be stale.",
"Changing public functions without reviewing callers and tests."
],
"faq": [
{
"question": "What does this skill connect to?",
"answer": "It expects AI Maestro to expose a local API and graph scripts on the workstation."
},
{
"question": "Does it require Bash?",
"answer": "Yes. The skill is built around Bash commands for graph queries and indexing."
},
{
"question": "Can it work without an indexed graph?",
"answer": "No. The project must be indexed before dependency queries can return useful results."
},
{
"question": "Does it send code to an external service?",
"answer": "No evidence of external network access was found. The documented API endpoint is localhost."
},
{
"question": "Why review commands before use?",
"answer": "The skill runs PATH-resolved scripts that are not included in the reviewed package."
},
{
"question": "Who benefits most from this skill?",
"answer": "Developers who need dependency context before refactoring or changing shared code benefit most."
}
]
},
"file_structure": [
{
"name": "output.json",
"type": "file",
"path": "output.json",
"lines": 169
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 160
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |