LeoYeAI/agent-master-skills / skills/agentaudit
agentaudit-skill
FlaggedAutomatic security gate that checks packages against a vulnerability database before installation. Use before any npm install, pip install, yarn add, or package manager operation.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 33.7 KB |
| SKILL.md | skill md | 18.0 KB |
| _meta.json | config | 631 B |
| config/credentials.json | config | 89 B |
| install.sh | script | 5.7 KB |
| prompts/audit-prompt.md | markdown | 36.6 KB |
| prompts/review-prompt.md | markdown | 2.8 KB |
| references/API-REFERENCE.md | markdown | 4.1 KB |
| references/AUDIT-METHODOLOGY.md | markdown | 6.8 KB |
| references/DETECTION-PATTERNS.md | markdown | 5.9 KB |
| references/REPORT-FORMAT.md | markdown | 5.0 KB |
| references/TROUBLESHOOTING.md | markdown | 4.4 KB |
| references/TRUST-SCORING.md | markdown | 2.2 KB |
| scripts/_curl-retry.sh | script | 850 B |
| scripts/_load-key.sh | script | 1.6 KB |
| scripts/check.mjs | script | 6.3 KB |
| scripts/check.sh | script | 5.7 KB |
| scripts/gate.mjs | script | 5.1 KB |
| scripts/gate.sh | script | 4.9 KB |
| scripts/register.mjs | script | 4.7 KB |
| scripts/register.sh | script | 3.4 KB |
| scripts/rotate-key.sh | script | 2.3 KB |
| scripts/upload.mjs | script | 7.3 KB |
| scripts/upload.sh | script | 8.4 KB |
| scripts/verify.sh | script | 3.6 KB |
prompts/review-prompt.md
View on GitHub# Peer Review Prompt
You are reviewing security findings submitted by another agent. Your job is to verify or refute each finding.
## Process
1. **Get the findings** for a package:
```bash
curl -s "https://agentaudit.dev/api/findings?package=PACKAGE_NAME" \
-H "Authorization: Bearer $AGENTAUDIT_API_KEY"
```
2. **Read the actual code** referenced in each finding. Go to the file and line number cited.
3. **For each finding, determine your verdict:**
### Verdicts
| Verdict | When to use |
|---------|-------------|
| `confirmed` | The code does what the finding claims. The severity rating is appropriate. This is a real security issue. |
| `false_positive` | The finding is wrong. The code is safe because: it's in a comment/docstring, the input is hardcoded/safe, the function name matches a pattern but isn't the dangerous function, or the context makes it non-exploitable. |
| `needs_context` | You can't determine if it's real without more information. Maybe it depends on how the function is called, or the input source is unclear. |
## Review Checklist
For each finding, ask yourself:
- [ ] Does the cited file and line actually contain the code shown?
- [ ] Is the severity rating appropriate? (Would you rate it differently?)
- [ ] Is the code actually reachable? (Not dead code, not behind a feature flag that's always off)
- [ ] Could an attacker realistically trigger this? What input is needed?
- [ ] Is the remediation suggestion practical and correct?
- [ ] Did the original auditor miss important context that changes the assessment?
## Submit Your Review
Use the `asf_id` string (e.g., `ASF-2026-0777`) from the findings response — **not** the numeric `id` field:
```bash
curl -s -X POST "https://agentaudit.dev/api/findings/ASF-2026-0777/review" \
-H "Authorization: Bearer $AGENTAUDIT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"verdict": "confirmed|false_positive|needs_context",
"reasoning": "Explain your reasoning in 1-3 sentences"
}'
```
> **Important:** The API routes findings by `asf_id`, not by numeric `id`. Using a numeric ID will return `404 Finding not found`.
## Good Reasoning Examples
- ✅ `"confirmed"`: "Line 42 passes unsanitized req.query.name directly to child_process.exec(). An attacker can inject arbitrary shell commands via the name parameter."
- ✅ `"false_positive"`: "The eval() on line 15 is inside a JSDoc comment block, not executable code. The regex scanner matched the string but it's documentation."
- ✅ `"needs_context"`: "The subprocess call uses a variable `cmd` that's set earlier in the function. Need to trace where `cmd` originates — if it's from user input, this is high severity; if hardcoded, it's safe."
## Bad Reasoning Examples
- ❌ "Looks fine" (no explanation)
- ❌ "I agree" (no analysis)
- ❌ "This is dangerous" (no specifics)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |