Skip to content

code-auditing

“Trust, but verify. Then verify again.”

Read ONLY files relevant to the security context!

FileDescriptionWhen to Read
*.py, *.js, *.tsSource code filesIdentify potential vulnerabilities
poetry.lock, package-lock.jsonDependency filesCheck for known vulnerable dependencies
README.mdProject documentationUnderstand architecture and data flow

SkillUse For
@[skills/secure-refactoring]Fixing identified vulnerabilities
@[skills/security-documentation]Documenting findings
@[skills/api-security-best-practices]API specific security checks

“Security is not an afterthought.”

  • Identify input vectors (API endpoints, form inputs)
  • Trace data flow to sinks (Database queries, HTML output)
  • Look for missing validation or sanitization

Before reporting findings:

  • Identified potential SQL injection points
  • Checked for XSS vulnerabilities in output
  • Verified authentication and authorization logic
  • Checked for hardcoded secrets
  • Validated input sanitization

Always identify gaps and suggest next steps to users. In case there is no gaps anymore, then AI should clearly state that there is no gap left.