@wrsmith108/claude-skill-security-auditor
BRun structured security audits with actionable remediation plans.
Install
agr install @wrsmith108/claude-skill-security-auditor --target claudeWrites 3 files into .claude/skills/, pinned to git-057418ff.
- .claude/skills/claude-skill-security-auditor/README.md
- .claude/skills/claude-skill-security-auditor/SKILL.md
- .claude/skills/claude-skill-security-auditor/package.json
Document
Security Auditor Skill
Run structured security audits with actionable remediation plans.
Trigger Phrases
- "npm audit"
- "security vulnerability"
- "dependency vulnerability"
- "CVE"
- "security check"
- "audit dependencies"
- "check vulnerabilities"
Description
This skill performs comprehensive security audits on npm projects, parsing vulnerability data and generating actionable remediation plans with prioritized fixes.
Capabilities
- Execute
npm audit --jsonand parse structured output - Classify vulnerabilities by severity (critical, high, medium, low)
- Extract CVE identifiers, affected versions, and fix versions
- Distinguish direct vs transitive dependencies
- Generate markdown reports with remediation commands
- Support risk acceptance via
security-exceptions.json - Provide CI-friendly exit codes
Usage
Basic Audit
npx tsx scripts/index.ts
JSON Output
npx tsx scripts/index.ts --json
Fail on High+ Severity (for CI)
npx tsx scripts/index.ts --fail-on high
Fail on Critical Only
npx tsx scripts/index.ts --fail-on critical
Risk Acceptance
Create a security-exceptions.json file in your project root to accept known risks:
{
"exceptions": [
{
"id": "GHSA-xxxx-xxxx-xxxx",
"reason": "Not exploitable in our usage context",
"expires": "2025-06-01",
"approvedBy": "security-team"
}
]
}
Exit Codes
0- No vulnerabilities above threshold1- Vulnerabilities found above threshold (with--fail-on)2- Error running audit
Requirements
- Node.js and npm installed
- Valid
package.jsonin target directory - Optional:
package-lock.jsonfor accurate audit
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-057418ff9e9b2026-07-31