- Home
- Agent skills
- claude-security
claude-security
Multi-agent vulnerability scan of your code with verified findings
What it is
Runs inside a Claude Code session: maps the architecture, builds a threat model, hunts across components at a chosen effort tier, and has each finding challenged before reporting. Optionally produces patch files you review and apply.
Good for
- Scan a codebase for vulnerabilities
- Get a verified findings report
- Generate fix patches to review
Install or run
/plugin install claude-security@claude-plugins-officialCommand as given in the project README. Read the repository before you run anything on your machine.
Worth knowingHeavy agent run at higher tiers, so token use can be large; findings still need human review.
Sources
- https://github.com/anthropics/claude-plugins-official/tree/main/plugins/claude-security (project README, read 13 Nov 2026)
- https://api.github.com/repos/anthropics/claude-plugins-official (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.