Learn-skills.dev security-reviewer
Security code reviewer. Use when performing security audits, reviewing code for vulnerabilities, or hardening applications. Covers OWASP Top 10 and common vulnerability patterns.
install
source · Clone the upstream repo
git clone https://github.com/NeverSight/learn-skills.dev
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/ai-engineer-agent/ai-engineer-skills/security-reviewer" ~/.claude/skills/neversight-learn-skills-dev-security-reviewer && rm -rf "$T"
manifest:
data/skills-md/ai-engineer-agent/ai-engineer-skills/security-reviewer/SKILL.mdsource content
Security Review
Perform a comprehensive security review of $ARGUMENTS:
Check for OWASP Top 10
-
Injection (SQL, NoSQL, OS Command, LDAP)
- Look for string concatenation in queries
- Check for parameterized queries / prepared statements
- Check for ORM misuse (raw queries)
-
Broken Authentication
- Check password hashing (bcrypt/scrypt/argon2, not MD5/SHA1)
- Check session management and token expiry
- Look for hardcoded credentials
-
Sensitive Data Exposure
- Check for secrets in code (API keys, passwords, tokens)
- Verify encryption at rest and in transit
- Check logging for PII/sensitive data leaks
-
XML External Entities (XXE)
- Check XML parser configuration
- Verify external entity processing is disabled
-
Broken Access Control
- Check authorization on every endpoint
- Look for IDOR vulnerabilities
- Verify RBAC/ABAC implementation
-
Security Misconfiguration
- Check HTTP headers (CORS, CSP, HSTS)
- Look for debug mode in production
- Check default credentials
-
Cross-Site Scripting (XSS)
- Check output encoding/escaping
- Look for
,dangerouslySetInnerHTML
,innerHTML| safe - Verify CSP headers
-
Insecure Deserialization
- Check for untrusted deserialization
- Verify input validation before deserialization
-
Using Components with Known Vulnerabilities
- Check for outdated dependencies
- Run
/npm audit
/pip auditcargo audit
-
Insufficient Logging & Monitoring
- Verify auth events are logged
- Check for sensitive data in logs
Output Format
Provide findings as:
- CRITICAL: Exploitable vulnerabilities
- HIGH: Likely exploitable or high-impact issues
- MEDIUM: Defense-in-depth improvements
- LOW: Best practice recommendations
For each finding: describe the issue, show the vulnerable code, explain the risk, and provide the fix.