skills/1-security-audit/SKILL.md
Phase 1 of security audit pipeline. Scans the codebase for vulnerabilities and creates SECURITY_PLAN.md. Use after /full-security-audit or invoke directly to start a security review. Say 'security audit phase 1' or run '/1-security-audit'.
npx skillsauth add opsmachine/om-agency 1-security-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scan the codebase and produce a prioritized findings list. Output lives in SECURITY_PLAN.md.
Scan src/app (or configured API folder) for:
supabase-security/SKILL.md for Supabase-specific patterns to checkOutput: Create or overwrite SECURITY_PLAN.md in the project root. List all findings as Pending with severity (Critical / High / Medium / Low) and file location.
Stop. Display a summary of findings to the user.
The next step is Phase 2: /2-security-critique
testing
Phase 2 of security audit pipeline. Red team review of Phase 1 findings — removes false positives, adds missed risks, ranks the backlog. Invoke with '/2-security-critique' after Phase 1 is complete.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.