← Explore all agents

SECURITY WORKFLOW COMPONENTS / Anthropic

Claude Security patch generator

A security-fix component that stages one narrow change in an orchestrator-created scratch checkout.

“Claude Security component for preparing one scoped security fix in an orchestrator-created scratch workspace.”

01 / THE REASONING

Why this made the selection.

  • It locates drifted findings by snippet and symbol rather than trusting old line numbers.
  • It must disclose behavior changes, make no change when the finding is already defeated, and let an independent verifier judge the staged result.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • plugins/claude-security/agents/patch-generator.md (pinned complete source retained)
  • plugins/claude-security/LICENSE
  • Repository README and current official host configuration documentation
  • plugins/claude-security/skills/claude-security/jobs/suggest-patches.md
  • plugins/claude-security/agents/explore.md
  • plugins/claude-security/LICENSE (overrides repository-wide licence for this plugin)

Our findings

  • It locates drifted findings by snippet and symbol rather than trusting old line numbers.
  • It must disclose behavior changes, make no change when the finding is already defeated, and let an independent verifier judge the staged result.
  • The exact-revision plugin licence is proprietary and expressly covers prompts, agent/skill definitions, workflows, code and documentation; the root Apache licence does not license this plugin for redistribution.

Not established by this review

  • Source review only: no agent was installed or invoked. Task correctness, effective host restrictions and integration behaviour were not tested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Use the role in your project.

Upstream setup instructions ↗
  1. Read the plugin-specific proprietary licence at this revision. Obtain the plugin from Anthropic and use/modify it only within the applicable authorized Anthropic-product agreement; this catalogue provides no copy for installation.
  2. Read the pinned source and its licence, then configure an explicitly bounded host context.
  3. Use only with the matching suggest-patches orchestration and disposable scratch clone; never substitute a shared working tree for WORKSPACE.
  4. Supply one finding, absolute scratch path and the patch base selected by the fix job.

Before you start

  • Matching Claude Security plugin and orchestration
  • Authorized repository and scratch-workspace context

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/anthropics/claude-plugins-official/blob/641d925db5a662e72f8650cb1b7670a59dab1abc/plugins/claude-security/agents/patch-generator.md

    Supports: Workflow, inputs, outputs and stated boundaries

  2. Applicable licence ↗Checked

    https://github.com/anthropics/claude-plugins-official/blob/641d925db5a662e72f8650cb1b7670a59dab1abc/plugins/claude-security/LICENSE

    Supports: Redistribution and attribution

  3. https://code.claude.com/docs/en/sub-agents.md

    Supports: Host loading and effective permission boundaries

  4. https://github.com/anthropics/claude-plugins-official/blob/641d925db5a662e72f8650cb1b7670a59dab1abc/plugins/claude-security/skills/claude-security/jobs/suggest-patches.md

    Supports: Dependency setup and source-review boundary

  5. https://github.com/anthropics/claude-plugins-official/blob/641d925db5a662e72f8650cb1b7670a59dab1abc/plugins/claude-security/agents/explore.md

    Supports: Dependency setup and source-review boundary

Evidence & Ask