Agent skills by task
Agent Skills for Security Audits and Vulnerability Review
Security skills give an agent an auditor’s method: map the attack surface first, run static analysis with real rules, check findings before reporting them, and look at the supply chain and CI as well as the code you wrote.
- skills
- 3
- packs
- 3
The skills
In the order we would try them
-
/security-and-hardeningStarts from a quick STRIDE threat model, then applies always, ask-first and never rules for input, auth and secrets.
-
/ponytail-auditRank what to fix first across a whole repositoryMaps the whole repo's entry points and data flows, then ranks up to 20 findings and says what to fix first.
-
/csoRun a security audit that keeps evidence separate from claimsAudits code, infrastructure, supply chain or skills for exploitable defects, challenges each finding and can reproduce fixes in Docker.
Questions
Can a skill replace a professional security audit?
No. These skills make an agent follow a sound audit method and use real tools, which catches many common issues. Critical systems still need a human review.
Do the static-analysis skills install Semgrep or CodeQL for me?
The skills tell the agent how to run and read those tools. The tools themselves must be installed on your machine, and CodeQL has its own licence terms.
Skills for other jobs
Lists picked by trendhub from public skill packs. Each skill lives in its author’s repository; read the current text there before installing.