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/fo0/clawstash/security-reviewnpx skills add fo0/clawstash --skill security-reviewgit clone --depth 1 https://github.com/fo0/clawstashWrote 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/fo0/clawstash/security-review)<a href="https://agentmods.dev/skills/fo0/clawstash/security-review"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/security-review.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 | $0.00082 | $0.01537 |
| Opus 5 | $0.00041 | $0.00768 |
| Sonnet 5 | $0.00016 | $0.00307 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade B, and why
security-review scanned grade B with 1 finding 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 4d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- [ ] Cloud metadata endpoint (169.254.169.254) blocked from app egress where not needed Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review — Focused Vulnerability Audit
When to Use
- User says "/security-review", "security review", "audit for security", "check for vulnerabilities", "OWASP review"
- After implementing auth, payment, file-upload, deserialization, dynamic-code, or external-integration code
- Before merging high-risk PRs (auth, billing, admin endpoints, public APIs)
Scope
Diff-based by default. Full-codebase only on explicit user request (/security-review --full or "audit the whole codebase").
Workflow
1. git status + git diff -> identify changed files
2. Read CLAUDE.md "Architecture Principles" + env vars -> understand trust boundaries
3. (If GitNexus available) gitnexus_impact on changed auth/input symbols
4. Read every changed file completely
5. Evaluate against the OWASP-focused checklist below
6. Run security-relevant automated checks (see Tooling)
7. Fix findings inline (prefer over defer; security debt compounds)
8. Output standard Security Review Results table
9. For NOT-fixed findings -> BACKLOG.md with explicit Sev: P0/P1
Checklist — OWASP Top 10 + Common Pitfalls
A01 Broken Access Control
- Every write/delete endpoint checks ownership / role
- No
IDOR— direct object refs in URLs validated against caller - No "security through obscurity" — hidden routes still authenticated
- Admin functionality gated by explicit role check, not just hidden UI
A02 Cryptographic Failures
- Secrets not in source / not in commits / not in logs
- No DIY crypto — use platform/library primitives
- TLS for all external traffic; HSTS where applicable
- Password storage: argon2 / scrypt / bcrypt with appropriate cost; never MD5/SHA1
- No predictable IDs for security-sensitive resources (use UUIDv4 / ULID)
A03 Injection
- SQL: parameterized queries / ORM with bound params; never string concat
- OS: no
shell=True/ unescapedexec/ template-injected commands - LDAP / NoSQL / GraphQL: equivalent param-binding patterns
- HTML: contextual escaping; no
dangerouslySetInnerHTMLwith user input - Template engines run with autoescape ON
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.
- 4d ago First seen · 151 lines · 82 tokens per session scan B 4e32aa6181b4
security-review is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,537 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 14 tools: SearXNG + Exa AI search, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search, and service health. Trigger…
business-model-validator
Use when a prospect, new customer, or existing operator wants to know whether Zooza fits their business, or which Zooza features map to how they operate. No Zooza account required — works as a pure knowledge interview.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
spotify-mcp-doctor
Diagnose and repair NovaLux12/spotify-mcp-server failures — auth, permissions, devices, rate limits, OpenClaw wiring. Use when Spotify tool calls fail or setup stalls.
negotiate-terminology
Use when the user wants to set up their business vocabulary — what they call programmes, classes, sessions, trainers. Also use when the user says "you're using the wrong words" or this is their first session with Zooza MCP.
class-management
Use when the user wants to create a new class, group, or course in Zooza — e.g. "set up a Monday yoga class", "add a new group", "schedule a course". Guides through programme selection, venue, trainer, session pattern, and commits.