Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/falcoschaefer99-eng/michael-security-agent/security-auditnpx skills add falcoschaefer99-eng/michael-security-agent --skill security-auditgit clone --depth 1 https://github.com/falcoschaefer99-eng/michael-security-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/falcoschaefer99-eng/michael-security-agent/security-audit)<a href="https://agentmods.dev/skills/falcoschaefer99-eng/michael-security-agent/security-audit"><img src="https://agentmods.dev/badge/skills/falcoschaefer99-eng/michael-security-agent/security-audit.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03041 |
| Opus 5 | $0.00000 | $0.01520 |
| Sonnet 5 | $0.00000 | $0.00608 |
| Haiku 4.5 | $0.00000 | $0.00304 |
Grade A, and why
security-audit scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -H "Authorization: Bearer $KEY" -d "$(python3 -c 'print("x"*2000000)')" "$URL/endpoint" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. Test with curl where endpoints are accessible How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
Invoked via /security-audit, /michael, or when your orchestrator dispatches for security review.
Operating Modes
Quick Audit (deploy gate, ~5 min)
Use before deploys or for rapid pass/fail assessment.
- Grep for dangerous patterns (hardcoded secrets, innerHTML, eval, raw SQL)
- Check auth on all new/changed endpoints
- Verify input validation on new user inputs
- Scan for new dependencies with known vulnerabilities
- Verdict: PASS, PASS WITH NOTES, or BLOCK
Deep Review (threat model, ~30 min)
Use after feature sprints or when new trust boundaries are introduced.
- Map all entry points and data flows
- Identify trust boundaries (client/server, server/database, service/service)
- STRIDE threat analysis on each boundary
- Run full 10-category checklist below
- Test with curl where endpoints are accessible
- Dependency/supply chain review on new packages
- Full findings report with threat model summary
Incident Response
Use when a breach is suspected or a relevant CVE is disclosed.
See ~/.claude/agents/references/security-intel.md incident response playbook.
10-Category Audit Checklist
1. Path Traversal & File Access [OWASP A01] [NIST PR.AC, PR.DS]
- Every handler accepting path/file/territory/namespace params validates input
- Check for
../, null bytes (%00), URL-encoded traversal (%2e%2e%2f) - Paths/keys resolve within expected boundaries (allowlist, not blocklist)
- Validation on BOTH read AND write operations
- R2 object keys constructed from user input are validated (key traversal)
2. Authentication & Authorization [OWASP A01, A07] [NIST PR.AC, PR.AA]
- Every endpoint requires auth (no accidentally public routes)
- Auth comparison is timing-safe (
crypto.timingSafeEqual,crypto.subtle.verify, or equivalent) - API keys in
Authorization: Bearerheader, never in URL parameters - Tokens not logged or included in error responses
- Trust boundary mapping: who authenticates at each boundary?
- JWT:
algheader validated, expected algorithm enforced - OAuth:
redirect_urihardcoded, state parameter present, PKCE recommended - Role/tier values validated against allowlist at write boundary (never accept from client)
- WebSocket: auth on connection, not just first message
- IDOR prevention: verify resource ownership, not just authentication
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 249 lines · 0 tokens per session scan A 159176c21c4e
security-audit is a skill published in the GitHub repository falcoschaefer99-eng/michael-security-agent (10 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,041 tokens. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
exploiting-broken-function-level-authorization
Tests APIs for Broken Function Level Authorization (BFLA) vulnerabilities where regular users can invoke administrative functions or access privileged API endpoints by directly calling them. The tester identifies admin and privileged endpoints, then attempts to access them with regular user credentials by manipulating…
exploiting-excessive-data-exposure-in-api
Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. The tester intercepts API responses and analyzes them for leaked PII, internal identifiers, debug information, or sensitive business data that the UI does not…
performing-api-inventory-and-discovery
Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a…
performing-api-rate-limiting-bypass
Tests API rate limiting implementations for bypass vulnerabilities by manipulating request headers, IP addresses, HTTP methods, API versions, and encoding schemes to circumvent request throttling controls. The tester identifies rate limit headers, determines enforcement mechanisms, and attempts bypasses including…
testing-api-authentication-weaknesses
Tests API authentication mechanisms for weaknesses including broken token validation, missing authentication on endpoints, weak password policies, credential stuffing susceptibility, token leakage in URLs or logs, and session management flaws. The tester evaluates JWT implementation, API key handling, OAuth flows, and…
testing-api-for-mass-assignment-vulnerability
Tests APIs for mass assignment (auto-binding) vulnerabilities where clients can modify object properties they should not have access to by including additional parameters in API requests. The tester identifies writable endpoints, adds undocumented fields to request bodies (role, isAdmin, price, balance), and checks if…