claude-security

By Anthropic

Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents,…

Plugin · by anthropics · runs in Claude Code, Cowork, claude.ai · 1 skill, 8 agents, 3 hooks · listed 2026-07-22

Claude Code

claude plugin install claude-security

Source

Skills (1)

Skill claude-security

The Claude Security menu — pick a job: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches…

Any agent
```
npx skills add anthropics/claude-plugins-official --skill claude-security
```

Agents (8)

Agent claude-security

The dedicated Claude Security orchestrator. Hand it an unattended job — "fully scan this repository and patch what you find; I understand it will use a lot of tokens" — and it runs the whole thing…
Agent explore

Read-only code explorer that the plugin's other agents dispatch to map a codebase — locate files, trace how a flow is wired, find every caller of a symbol, answer "where does X happen".
Agent patch-generator

Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
Agent patch-verifier

The single verifier per fix round — reviews the workspace's staged diff against the finding, runs the tests, and states the three confidence claims a patch file must earn; dispatched by the fix job…
Agent scan-inventory

Restricted read-only repository cartographer dispatched by the Claude Security scan workflow to partition the tree into components and account for every top-level directory; not for direct…
Agent scan-loader

Restricted read-only loader dispatched by the Claude Security scan workflow to return one candidates file from the run directory; not for direct invocation.
Agent scan-researcher

Restricted read-only vulnerability researcher dispatched by the Claude Security scan workflow; not for direct invocation or general exploration.
Agent scan-verifier

Restricted read-only verifier dispatched by the Claude Security scan workflow to vote on one candidate finding; not for direct invocation.

From Anthropic's public plugin directory, read on 2026-10-15. Find a skill by task.