Summary
This runs security audits on code diffs, PRs, or branches with an emphasis on cutting false positives. It does a three-phase analysis (context research, pattern comparison, vulnerability assessment) and filters findings down to only high-confidence exploitable issues. Comes with GitHub Actions integration that can post inline PR comments, plus custom filtering rules and domain-specific scan templates for compliance or finserv workflows. The eval framework is nice: point it at any public PR to test against real code. The philosophy is refreshingly pragmatic: better to miss theoretical vulnerabilities than drown teams in noise. Only flags HIGH and MEDIUM severity issues with 8+ confidence scores.
Install to Claude Code
npx -y skills add leonmelamud/claude-code-security-review --skill code-security-audit --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
