Stats
Actions
Tags
From setup-ai
Audit code for exploitable security vulnerabilities — injection, auth/authorization flaws, secrets, trust-boundary violations, OWASP Top 10. Use when reviewing security-sensitive code (auth, payments, input handling) or when asked for a security audit. Defensive use only.
How this skill is triggered — by the user, by Claude, or both
Slash command
/setup-ai:security-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Find exploitable vulnerabilities and give a concrete fix for each. Defensive review only.
Find exploitable vulnerabilities and give a concrete fix for each. Defensive review only.
exec, spawn, raw query, eval, dangerouslySetInnerHTML,
string-built SQL/paths — then trace backward to the source..env, secrets leaked
to third parties.npm audit), permissive CORS, missing security
headers, dangerous framework defaults.Per finding: severity — file_path:line — attack path (1 sentence) — fix. If nothing exploitable,
say so and name the riskiest area to watch.
npx claudepluginhub linder3hs/setup-ai --plugin setup-aiBlocks Edit/Write/Bash actions until Claude investigates importers, data schemas, and user instructions. Improves output quality by forcing concrete facts before edits.