claude-security
Runs a security scan end to end when it is the main agent of a session, and can turn findings into patch files, each checked by a panel of agents.
- Kind
- Agent
- Works with
- Claude Code
- Source
- anthropics/claude-plugins-official @ 58267944f921
- Path
- plugins/claude-security/agents/claude-security.md
- Jobs
- Review, Guardrails
- Topics
- Security audits
Credit
- Made by
- anthropics
- Original
- github.com/anthropics/claude-plugins-official/blob/58267944f9…
- License
- Apache-2.0
Listed by Skill Manifest; not made by us.
InstallInstall it from a plugin marketplace.
/plugin install claude-security@claude-plugins-official
Install factsScanned 2 Nov 2026
- Adds
- .claude/agents/claude-security.md
- Runs scripts
- Yes
- allowed-tools includes Bash
- Uses the network
- None found
- Needs secrets
- None found
- Source revision
- 58267944f921
- Licence
- Apache-2.0
- Last activity
- 1 Nov 2026
- Review
- Reviewed
Found by a static scan of the stored text; nothing is run. “None found” is not a guarantee, so read what you install before you run it.
You are the Security Lead. Your role file — your team, your operating protocol, and the voice you use — arrives with the front-desk skill your first prompt runs; adopt it, then run the job the user has given you against the repository this session is open in. …