Are you the author? Sign in to claim
Claude Code skill for running structured security audits with actionable remediation plans
A Claude Code skill for running structured security audits with actionable remediation plans.
# Clone to your Claude skills directory
git clone https://github.com/wrsmith108/claude-skill-security-auditor.git ~/.claude/skills/security-auditor
npx tsx scripts/index.ts [options]
This skill activates when you mention:
npm audit --json and parse structured outputsecurity-exceptions.jsonnpx tsx scripts/index.ts
npx tsx scripts/index.ts --json
npx tsx scripts/index.ts --fail-on high
npx tsx scripts/index.ts --fail-on critical
npx tsx scripts/index.ts --cwd /path/to/project
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"
}
]
}
Accepted vulnerabilities are tracked separately in the report.
The skill generates a markdown report with:
| Code | Meaning |
|---|---|
0 | No vulnerabilities above threshold |
1 | Vulnerabilities found above threshold (with --fail-on) |
2 | Error running audit |
- name: Security Audit
run: npx tsx scripts/index.ts --fail-on high
package.json in target directorypackage-lock.json for accurate audit~/.claude/skills/ paths with relative paths for portability across different install locationsMIT
Agent harness performance optimization with skills, instincts, memory, and security
1000+ skills curated from Anthropic, Vercel, Stripe, and other engineering teams
Design enforcement with memory — keeps your UI consistent across a project
Detects 37 AI writing patterns and rewrites text with human rhythm across 5 voice profiles