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/chandrudp29/skillhub/security-reviewnpx skills add chandrudp29/skillhub --skill security-reviewgit clone --depth 1 https://github.com/chandrudp29/skillhubWrote 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/chandrudp29/skillhub/security-review)<a href="https://agentmods.dev/skills/chandrudp29/skillhub/security-review"><img src="https://agentmods.dev/badge/skills/chandrudp29/skillhub/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 5.1 | $0.00046 | $0.01353 |
| Opus 5 | $0.00023 | $0.00677 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
security-review scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(f"ffmpeg -i {user_filename} output.mp4") How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
A systematic security audit that finds real vulnerabilities — not theoretical ones. Prioritizes by blast radius.
When to Use
- Before any code ships to production
- When adding authentication, file upload, payments, or user data handling
- Reviewing a PR that touches auth, APIs, or data access
- Auditing a new codebase you inherited
The Audit Checklist
Work through these in order — critical first.
1. Secrets and Credentials
The easiest win. Scan first.
# Quick scan for likely secrets
grep -rE "(api_key|secret|password|token|credential)\s*=\s*['\"][^'\"]{8,}" . --include="*.py" --include="*.js" --include="*.ts" --include="*.env"
git log --all --full-history -- "**/*.env" "**/.env*"
Findings:
- No secrets hardcoded in source files
- No secrets in git history
-
.envfiles are in.gitignore - Secrets loaded from environment variables or a secrets manager (AWS Secrets Manager, Vault)
Severity: CRITICAL — hardcoded secrets are actively exploited within hours of being pushed.
2. Injection Vulnerabilities
SQL Injection — look for string concatenation in queries:
# VULNERABLE
query = f"SELECT * FROM users WHERE email = '{email}'"
cursor.execute(query)
# SAFE
cursor.execute("SELECT * FROM users WHERE email = %s", (email,))
Command Injection — look for user input in shell commands:
# VULNERABLE
os.system(f"ffmpeg -i {user_filename} output.mp4")
subprocess.call(f"convert {path}", shell=True)
# SAFE
subprocess.run(["ffmpeg", "-i", user_filename, "output.mp4"])
NoSQL Injection — look for unvalidated objects passed to MongoDB queries.
Template Injection — look for user strings rendered as templates (Jinja2, Handlebars).
Severity: CRITICAL for SQL/command injection. HIGH for others.
3. Authentication and Authorization
Authentication (who are you?):
- Passwords hashed with bcrypt/argon2 (never MD5, SHA1, or plain SHA256)
- JWT secrets are strong (≥256 bits) and not hardcoded
- JWT expiry is set (exp claim checked)
- Sessions invalidated on logout
- Rate limiting on login and password reset endpoints
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 168 lines · 46 tokens per session scan A 0ce52a0e2731
security-review is a skill published in the GitHub repository chandrudp29/skillhub (13 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,353 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
security-testing
Test for security vulnerabilities using OWASP principles. Use when conducting security audits, testing auth, or implementing security practices.
security-audit
Audit code and infrastructure for security vulnerabilities. Use when performing security reviews, checking for OWASP Top 10 issues, auditing dependencies, or hardening applications.
ship-safe
Run a full security audit on this project — 16 agents scan for secrets, injections, auth bypass, SSRF, supply chain, Supabase RLS, MCP security, agentic AI, RAG poisoning, PII compliance, and more. Use when the user wants a security audit, vulnerability scan, or asks if their code is safe to ship.
ship-safe-baseline
Manage your security baseline — accept current findings as known debt, then only report new regressions on future scans. Use when the user wants to adopt security scanning incrementally or suppress existing findings.
ship-safe-ci
Run Ship Safe in CI mode — compact output, exit codes, SARIF generation. Use when the user wants to set up CI/CD security gates or test their pipeline configuration.
ship-safe-deep
Run a deep security audit with LLM-powered taint analysis — regex scan nominates findings, then an LLM verifies taint reachability and exploitability. Use when the user wants thorough, high-confidence results with fewer false positives.