Borrowing it
Nothing to install: this file belongs to cohen-liel/hivemind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cohen-liel/hivemind/main/.claude/skills/security-review/SKILL.mdgit clone --depth 1 https://github.com/cohen-liel/hivemindWrote 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/cohen-liel/hivemind/security-review)<a href="https://agentmods.dev/skills/cohen-liel/hivemind/security-review"><img src="https://agentmods.dev/badge/skills/cohen-liel/hivemind/security-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cohen-liel/hivemind/security-review"><img src="https://agentmods.dev/badge/skills/cohen-liel/hivemind/security-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00673 |
| Opus 5 | $0.00015 | $0.00336 |
| Sonnet 5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
security-review scanned grade A with 0 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review Checklist
Authentication & Authorization
- Passwords hashed with bcrypt/argon2 (NEVER md5/sha1/plain)
- JWT tokens have expiry (access: 15min, refresh: 7d)
- JWT secret is long (32+ chars), loaded from env var
- Refresh token rotation implemented (old token invalidated on use)
- Rate limiting on login (max 5 attempts, then lockout/slowdown)
- CSRF protection on state-changing endpoints (cookies)
- Auth check on EVERY protected route (not just the frontend)
- Admin endpoints have separate, stricter auth check
Input Validation
- ALL user input validated server-side (never trust client)
- File uploads: check MIME type, extension, size limit, scan for malware
- URL parameters parsed and validated (no direct string concat in SQL)
- JSON bodies have max size limit (e.g., 1MB)
- HTML/Markdown user content sanitized before rendering (XSS)
SQL & Data
- ALL queries use parameterized statements (no f-string SQL)
- ORM used for CRUD — raw SQL only for complex analytics
- Database user has minimum required permissions (not superuser)
- Sensitive fields (password, SSN, CC) never returned in API responses
- PII encrypted at rest for sensitive columns
API Security
- CORS: explicit allowed origins (never
*in production) - Security headers: X-Content-Type-Options, X-Frame-Options, CSP
- HTTPS enforced (redirect HTTP → HTTPS)
- API keys/secrets never logged or included in error messages
- 4xx errors don't reveal internal details (stack traces, file paths)
Dependency Security
- No known CVEs in dependencies (run: pip audit / npm audit)
- Dependencies pinned to exact versions
- Secrets never in code or git history (use env vars / secrets manager)
- .env files in .gitignore
Common Vulnerabilities to Check
OWASP Top 10:
1. Broken Access Control — can user A see/edit user B's data?
2. Cryptographic Failures — are secrets/passwords properly protected?
3. Injection — SQL, command, LDAP injection possible?
4. Insecure Design — is auth logic correct by design?
5. Security Misconfiguration — debug mode on? default credentials?
6. Vulnerable Components — any known CVEs in deps?
7. Auth Failures — session fixation? weak tokens?
8. Data Integrity — deserialization attacks? tampered JWTs?
9. Logging Failures — are attacks logged? are secrets in logs?
10. SSRF — can attacker make server fetch internal URLs?
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.
- 9d ago First seen · 63 lines · 30 tokens per session scan A 194fded77a2f
security-review is a skill published in the GitHub repository cohen-liel/hivemind (108 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 673 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
pr-review-canvas
Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
cross-model-review
A second-opinion code review that asks a different AI model to independently inspect a change, then compares both reviews. It focuses on logic, security, consistency, and omissions.