Skip to content

aiskillstore/marketplace / skills/23blocks-os/ai-maestro-memory-search

ai-maestro-memory-search

Verified

PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.

FileKindSize
SKILL.mdskill md4.1 KB
skill-report.jsonconfig50.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-06T00:36:25.591Z",
    "slug": "23blocks-os-ai-maestro-memory-search",
    "source_url": "https://github.com/23blocks-OS/ai-maestro/tree/main/skills/memory-search",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "0d052c96d7e260930191df512eb09341ea4df1b912c3e3262b1a8c301907dce5",
    "tree_hash": "ddce2dd41b7e56887ccedb52479c14e6cbb860fbada8798a672c813a04dfc9b4",
    "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-memory-search",
    "description": "Search prior AI conversations for decisions, context, and earlier work before starting a new task.",
    "summary": "Helps AI agents recover prior conversation context before continuing work.",
    "icon": "📦",
    "version": "1.0.0",
    "author": "23blocks-OS",
    "license": "MIT",
    "tags": [
      "memory-search",
      "conversation-history",
      "context-retrieval",
      "agent-workflow",
      "developer-productivity"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "filesystem"
    ],
    "category": "productivity"
  },
  "security_audit": {
    "risk_level": "high",
    "is_blocked": false,
    "safe_to_publish": false,
    "analysis_status": "ok",
    "summary": "Several static external-command alerts are Markdown false positives, but the skill does instruct Bash execution of local helper scripts and an unaudited installer. I found no evidence of network exfiltration, but the forceful always-on memory behavior and conversation-history access create security and privacy concerns.",
    "remediation": [
      {
        "issue": "Forceful automatic behavior language",
        "suggestion": "Rephrase the instructions to respect higher-priority policies and user intent. Make memory search relevant and optional when the task does not need prior context.",
        "severity": "high"
      },
      {
        "issue": "Automatic conversation history access",
        "suggestion": "Require clear user consent or a scoped trigger before searching prior conversations. Avoid role-wide searches unless the user asks for them.",
        "severity": "medium"
      },
      {
        "issue": "Unaudited relative installer execution",
        "suggestion": "Remove the ./install-memory-tools.sh instruction or include the installer source for review. Tell users to inspect scripts before running them.",
        "severity": "high"
      },
      {
        "issue": "External helper scripts are not included",
        "suggestion": "Document the expected source, version, and path for memory-search.sh and doc-search.sh. Prefer pinned, auditable helper scripts.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 47
          },
          {
            "file": "SKILL.md",
            "line_start": 47,
            "line_end": 48
          },
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 59,
            "line_end": 60
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 61
          },
          {
            "file": "SKILL.md",
            "line_start": 61,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 81
          },
          {
            "file": "SKILL.md",
            "line_start": 81,
            "line_end": 87
          },
          {
            "file": "SKILL.md",
            "line_start": 87,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 105
          },
          {
            "file": "SKILL.md",
            "line_start": 105,
            "line_end": 109
          },
          {
            "file": "SKILL.md",
            "line_start": 109,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 126
          },
          {
            "file": "SKILL.md",
            "line_start": 126,
            "line_end": 128
          },
          {
            "file": "SKILL.md",
            "line_start": 128,
            "line_end": 130
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 130,
            "line_end": 130
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 130,
            "line_end": 130
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 33,
        "line_end": 38,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 38,
        "line_end": 46,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 47,
        "snippet": "| `memory-search.sh \"<query>\"` | Hybrid search (recommended) |"
      },
      {
        "id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 47,
        "line_end": 48,
        "snippet": "| `memory-search.sh \"<query>\" --mode semantic` | Find conceptually related |"
      },
      {
        "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": 49,
        "snippet": "| `memory-search.sh \"<query>\" --mode term` | Exact term matching |"
      },
      {
        "id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 49,
        "line_end": 50,
        "snippet": "| `memory-search.sh \"<query>\" --role user` | Only user messages |"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 56,
        "snippet": "| `memory-search.sh \"<query>\" --role assistant` | Only your responses |"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 57,
        "snippet": "| \"Continue working on X\" | `memory-search.sh \"X\"` |"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "| \"Fix the issue we discussed\" | `memory-search.sh \"issue\"`, `memory-search.sh \"bug\"` |"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 58,
        "snippet": "| \"Use the approach we agreed on\" | `memory-search.sh \"approach\"`, `memory-search.sh \"decision\"` |"
      },
      {
        "id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 59,
        "line_end": 60,
        "snippet": "| \"Like we did before\" | `memory-search.sh \"<topic> implementation\"` |"
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 60,
        "line_end": 61,
        "snippet": "| Any specific feature/component | `memory-search.sh \"<feature>\"` |"
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 61,
        "line_end": 65,
        "snippet": "| References to past work | `memory-search.sh \"<reference>\" --mode semantic` |"
      },
      {
        "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": 81,
        "snippet": "```bash"
      },
      {
        "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": "```"
      },
      {
        "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": 88,
        "snippet": "| `hybrid` (default) | General search, best for most cases |"
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 88,
        "line_end": 89,
        "snippet": "| `semantic` | Looking for related concepts, different wording |"
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 90,
        "snippet": "| `term` | Looking for exact function/class names |"
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 105,
        "snippet": "| `symbol` | Looking for code symbols mentioned |"
      },
      {
        "id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 105,
        "line_end": 109,
        "snippet": "```bash"
      },
      {
        "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": 119,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 119,
        "line_end": 120,
        "snippet": "- Check PATH: `which memory-search.sh`"
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 121,
        "snippet": "- Verify scripts installed: `ls -la ~/.local/bin/memory-*.sh`"
      },
      {
        "id": "external_commands:SKILL.md:121:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 126,
        "snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
      },
      {
        "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": 128,
        "snippet": "```bash"
      },
      {
        "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": 130,
        "snippet": "```"
      },
      {
        "id": "filesystem:SKILL.md:120:hidden-file-in-home-directory",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Hidden file in home directory",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 120,
        "snippet": "- Verify scripts installed: `ls -la ~/.local/bin/memory-*.sh`"
      },
      {
        "id": "filesystem:SKILL.md:121:hidden-file-in-home-directory",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Hidden file in home directory",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 121,
        "snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
      },
      {
        "id": "filesystem:SKILL.md:130:hidden-file-in-home-directory",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Hidden file in home directory",
        "file": "SKILL.md",
        "line_start": 130,
        "line_end": 130,
        "snippet": "This installs scripts to `~/.local/bin/`."
      },
      {
        "id": "filesystem:SKILL.md:120:hidden-file-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Hidden file access",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 120,
        "snippet": "- Verify scripts installed: `ls -la ~/.local/bin/memory-*.sh`"
      },
      {
        "id": "filesystem:SKILL.md:121:hidden-file-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Hidden file access",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 121,
        "snippet": "- Scripts are installed to `~/.local/bin/` which should be in your PATH"
      },
      {
        "id": "filesystem:SKILL.md:130:hidden-file-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Hidden file access",
        "file": "SKILL.md",
        "line_start": 130,
        "line_end": 130,
        "snippet": "This installs scripts to `~/.local/bin/`."
      },
      {
        "id": "blocker:SKILL.md:15:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 15,
        "line_end": 15,
        "snippet": "- **Past decisions** - What did we decide last time?"
      },
      {
        "id": "blocker:SKILL.md:17:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 17,
        "snippet": "- **Earlier work** - Did we already start on this?"
      },
      {
        "id": "blocker:SKILL.md:46:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 46,
        "snippet": "| `memory-search.sh \"<query>\"` | Hybrid search (recommended) |"
      },
      {
        "id": "blocker:SKILL.md:59:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 59,
        "line_end": 59,
        "snippet": "| \"Like we did before\" | `memory-search.sh \"<topic> implementation\"` |"
      },
      {
        "id": "blocker:SKILL.md:107:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 107,
        "line_end": 107,
        "snippet": "memory-search.sh \"feature\"       # What did we discuss?"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is a Markdown fence delimiter or documentation boundary, not Ruby or shell backtick execution. No executable command is present on this finding line."
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is a Markdown fence delimiter or documentation boundary, not Ruby or shell backtick execution. No executable command is present on this finding line."
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.72,
        "reason": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.73,
        "reason": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.76,
        "reason": "The bash example block directs the agent to run memory-search.sh with several queries and role filters. The helper script is external to the package and cannot be audited here.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is a Markdown fence delimiter or documentation boundary, not Ruby or shell backtick execution. No executable command is present on this finding line."
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks format search mode names in Markdown. They do not execute code or pass data to a shell."
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks format search mode names in Markdown. They do not execute code or pass data to a shell."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks format search mode names in Markdown. They do not execute code or pass data to a shell."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks format search mode names in Markdown. They do not execute code or pass data to a shell."
      },
      {
        "id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.75,
        "reason": "The bash example combines memory-search.sh and doc-search.sh, both external commands. Their implementations are not included, so command behavior depends on the local environment.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is a Markdown fence delimiter or documentation boundary, not Ruby or shell backtick execution. No executable command is present on this finding line."
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "which memory-search.sh is a fixed PATH diagnostic with no user input and no state change. It is not a command injection pattern."
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.78,
        "reason": "The ls command is a fixed troubleshooting directory listing for a standard user binary path. It does not execute arbitrary input."
      },
      {
        "id": "external_commands:SKILL.md:121:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This line describes an install destination in prose. It does not contain executable syntax or a shell command to run."
      },
      {
        "id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.87,
        "reason": "The bash installation block runs ./install-memory-tools.sh, a relative installer not present in the package. This could execute an unreviewed local script.",
        "severity": "high"
      },
      {
        "id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This is a Markdown fence delimiter or documentation boundary, not Ruby or shell backtick execution. No executable command is present on this finding line."
      },
      {
        "id": "filesystem:SKILL.md:120:hidden-file-in-home-directory",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "filesystem:SKILL.md:121:hidden-file-in-home-directory",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "filesystem:SKILL.md:130:hidden-file-in-home-directory",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "filesystem:SKILL.md:120:hidden-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "filesystem:SKILL.md:121:hidden-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "filesystem:SKILL.md:130:hidden-file-access",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The referenced path is ~/.local/bin, a conventional per-user executable directory. The evidence shows troubleshooting or install documentation, not secret file access or broad home directory traversal."
      },
      {
        "id": "blocker:SKILL.md:15:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The text concerns conversation memory and prior work, not operating system reconnaissance. No host enumeration or sensitive system discovery is shown."
      },
      {
        "id": "blocker:SKILL.md:17:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The text concerns conversation memory and prior work, not operating system reconnaissance. No host enumeration or sensitive system discovery is shown."
      },
      {
        "id": "blocker:SKILL.md:46:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The text concerns conversation memory and prior work, not operating system reconnaissance. No host enumeration or sensitive system discovery is shown."
      },
      {
        "id": "blocker:SKILL.md:59:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The text concerns conversation memory and prior work, not operating system reconnaissance. No host enumeration or sensitive system discovery is shown."
      },
      {
        "id": "blocker:SKILL.md:107:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The text concerns conversation memory and prior work, not operating system reconnaissance. No host enumeration or sensitive system discovery is shown."
      }
    ],
    "semantic_findings": [
      {
        "title": "Prompt Injection Attempt Detected",
        "description": "The skill says \"THIS IS NOT OPTIONAL\" and tries to make memory search the default behavior for every task. This can override user intent and higher-priority workflow decisions.",
        "severity": "high",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 9,
            "line_end": 31
          }
        ],
        "confidence": 0.82,
        "confidence_reasoning": "The file uses imperative authority language to force behavior for every task. It does not target this audit directly, so confidence is high but not absolute."
      },
      {
        "title": "Automatic Conversation History Access",
        "description": "The skill instructs the agent to search previous discussions, prior context, and role-filtered user or assistant messages before work begins. This creates a privacy risk if installed without clear consent.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 25,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 50
          }
        ],
        "confidence": 0.9,
        "confidence_reasoning": "The instructions directly require memory searches and include role filters for user and assistant messages. No network exfiltration is shown, so severity remains medium."
      }
    ],
    "critical_findings": [],
    "high_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 126,
            "line_end": 128
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.87,
        "confidence_reasoning": "The bash installation block runs ./install-memory-tools.sh, a relative installer not present in the package. This could execute an unreviewed local script."
      },
      {
        "title": "Prompt Injection Attempt Detected",
        "description": "The skill says \"THIS IS NOT OPTIONAL\" and tries to make memory search the default behavior for every task. This can override user intent and higher-priority workflow decisions.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 9,
            "line_end": 31
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "high",
        "confidence": 0.82,
        "confidence_reasoning": "The file uses imperative authority language to force behavior for every task. It does not target this audit directly, so confidence is high but not absolute."
      }
    ],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "| `memory-search.sh \"<query>\"` | Hybrid search (recommended) |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 47
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| `memory-search.sh \"<query>\" --mode semantic` | Find conceptually related |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 47,
            "line_end": 48
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| `memory-search.sh \"<query>\" --mode term` | Exact term matching |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 49
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| `memory-search.sh \"<query>\" --role user` | Only user messages |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 50
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| `memory-search.sh \"<query>\" --role assistant` | Only your responses |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 56
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.72,
        "confidence_reasoning": "This line instructs the agent to invoke memory-search.sh from the shell with query text. The script is PATH-resolved and not included for review."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| \"Continue working on X\" | `memory-search.sh \"X\"` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 57
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| \"Fix the issue we discussed\" | `memory-search.sh \"issue\"`, `memory-search.sh \"bug\"` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| \"Use the approach we agreed on\" | `memory-search.sh \"approach\"`, `memory-search.sh \"decision\"` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 58
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| \"Like we did before\" | `memory-search.sh \"<topic> implementation\"` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 59,
            "line_end": 60
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| Any specific feature/component | `memory-search.sh \"<feature>\"` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 61
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| References to past work | `memory-search.sh \"<reference>\" --mode semantic` |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 61,
            "line_end": 65
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.73,
        "confidence_reasoning": "This table maps user requests to immediate memory-search.sh shell invocations. The query comes from user context and the external helper is not auditable in this package."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 81
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.76,
        "confidence_reasoning": "The bash example block directs the agent to run memory-search.sh with several queries and role filters. The helper script is external to the package and cannot be audited here."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 105,
            "line_end": 109
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.75,
        "confidence_reasoning": "The bash example combines memory-search.sh and doc-search.sh, both external commands. Their implementations are not included, so command behavior depends on the local environment."
      },
      {
        "title": "Automatic Conversation History Access",
        "description": "The skill instructs the agent to search previous discussions, prior context, and role-filtered user or assistant messages before work begins. This creates a privacy risk if installed without clear consent.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 25,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 50
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.9,
        "confidence_reasoning": "The instructions directly require memory searches and include role filters for user and assistant messages. No network exfiltration is shown, so severity remains medium."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 131,
    "audit_model": "codex",
    "audited_at": "2026-07-06T00:36:25.591Z",
    "agent_auto_install_policy": "confirmation_required",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Search Prior AI Conversation Memory",
    "value_statement": "AI agents lose context across sessions and may repeat past work. This skill directs Claude, Codex, and Claude Code to search prior conversations before acting.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "AI Maestro",
      "memory search",
      "conversation history",
      "context retrieval",
      "agent workflow",
      "developer productivity",
      "prior decisions"
    ],
    "actual_capabilities": [
      "Directs agents to search conversation history before starting new work.",
      "Provides memory search command patterns for hybrid, semantic, and term search.",
      "Supports role filters for user messages and assistant responses.",
      "Suggests searches for bugs, decisions, features, and prior implementations.",
      "Shows how to combine memory search with documentation search.",
      "Includes troubleshooting steps for missing local memory tools."
    ],
    "limitations": [
      "Requires memory-search.sh to be installed and available on PATH.",
      "The package does not include the helper scripts or search index.",
      "Requires Bash access, so restricted environments cannot use every workflow.",
      "Search quality depends on available conversation history and indexing."
    ],
    "use_cases": [
      {
        "title": "Resume Development Work",
        "description": "Recover prior requirements, decisions, and partial implementation context before editing files.",
        "target_user": "Software developers"
      },
      {
        "title": "Avoid Repeated Answers",
        "description": "Find previous explanations before responding, so the agent can build on existing context.",
        "target_user": "AI coding agents"
      },
      {
        "title": "Review Prior Decisions",
        "description": "Locate earlier choices about architecture, bugs, or product behavior before planning new work.",
        "target_user": "Technical leads"
      }
    ],
    "prompt_templates": [
      {
        "title": "Find Prior Context",
        "scenario": "Beginner prompt for a simple topic lookup.",
        "prompt": "Search memory for previous discussions about [topic], then summarize the relevant decisions before starting."
      },
      {
        "title": "Continue Earlier Work",
        "scenario": "Intermediate prompt for resuming a feature or fix.",
        "prompt": "Search for past work on [feature], identify what remains, and explain the next implementation step."
      },
      {
        "title": "Compare Memory And Docs",
        "scenario": "Advanced prompt for reconciling prior context with current documentation.",
        "prompt": "Search memory and documentation for [component], then list prior decisions, current guidance, and conflicts."
      },
      {
        "title": "Investigate Repeated Issue",
        "scenario": "Advanced prompt for recurring bugs or regressions.",
        "prompt": "Search user and assistant history for [bug], group prior fixes, and recommend the safest next action."
      }
    ],
    "output_examples": [
      {
        "input": "User asks: Continue the authentication work from last time.",
        "output": "Found prior decisions about session storage and remaining validation work. Start by checking the existing branch and tests."
      },
      {
        "input": "User asks: Fix the issue we discussed with payments.",
        "output": [
          "Prior context points to a retry failure after payment authorization.",
          "The next step is to inspect the payment service logs and related tests."
        ]
      },
      {
        "input": "User asks: Use the approach we agreed on for error handling.",
        "output": "Previous discussion favored typed error results with centralized logging. Apply that pattern before adding new exception paths."
      }
    ],
    "best_practices": [
      "Search only for terms that are relevant to the current user request.",
      "Summarize found context before acting on it.",
      "Treat missing search results as useful context, not as a failure."
    ],
    "anti_patterns": [
      "Do not run memory searches for unrelated or sensitive topics.",
      "Do not treat search results as current facts without verification.",
      "Do not install helper scripts without reviewing their source."
    ],
    "faq": [
      {
        "question": "What does this skill do?",
        "answer": "It tells an AI agent to search prior conversation history before starting work."
      },
      {
        "question": "Which tools does it support?",
        "answer": "The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "Does it include the search scripts?",
        "answer": "No. The package contains instructions, but the helper scripts are not included."
      },
      {
        "question": "Does it need shell access?",
        "answer": "Yes. The documented workflows use Bash commands such as memory-search.sh."
      },
      {
        "question": "Can it search only user or assistant messages?",
        "answer": "Yes. The instructions describe role filters for user messages and assistant responses."
      },
      {
        "question": "What should users verify before using it?",
        "answer": "Users should verify the installed helper scripts, PATH target, and conversation data scope."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 131
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall