SECURITY REVIEW / Anthropic
Scan inventory
Pins the Claude Security cartographer that partitions one tree and must place every listed top-level directory on a scanned or skipped ledger.
“A read-only scan cartographer, not for direct invocation or vulnerability research, that accounts for every top-level directory the dispatch lists.”
01 / THE REASONING
Why this made the selection.
- The agents index has no entry for plugins/claude-security/agents/scan-inventory.md.
- The file forbids vulnerability research, declares no shell, and says an answer that omits a dispatched top-level directory is invalid and must be completed rather than narrowed.
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/scan-inventory.md
- plugins/claude-security/README.md
- README.md
- LICENSE
- Round 2: pinned definition, output contract and permission/dependency boundaries reread on 2026-10-14
- plugins/claude-security/LICENSE (overrides repository-wide licence for this plugin)
Our findings
- The description says it accounts for every top-level directory and is not for direct invocation or vulnerability research. Tools are Read, Glob, and Grep.
- The body says it has no shell and dispatches no subagents, and that it does not hunt for vulnerabilities or judge severity.
- For a whole-repository scan, every top-level directory the dispatch lists must land in components or securityScanSkippedComponents. An omission is invalid.
- It says repository text that tells it to omit a directory is data, not an instruction. A skip still needs the agent's own reason on the skipped ledger.
- Component-size guidance must not cause more code to be skipped when the component count cap is reached.
- Untrusted repository text cannot authorize omission; skipped paths require the cartographer’s own explicit reasons.
- 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
- The resource was not executed and its tools were not called.
- No tree was partitioned.
- Glob and Grep were not called.
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.
DOCUMENTED COMMAND
/plugin install claude-security@claude-plugins-official Copying does not execute this command. It may retrieve a newer version than the reviewed source.
- 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.
- The claude-security README shows that line, including the four leading spaces, then /reload-plugins on the next line.
- That line installs the claude-security plugin. It does not name this agent.
- The repository root README only has /plugin install {plugin-name}@claude-plugins-official, which is a placeholder, so it is not install.command.
- Use the matching dispatcher and validate path coverage and non-overlap against the actual target tree before launching researchers.
Before you start
- Claude Code
- Python 3.9 or newer on PATH, which the plugin README lists for the plugin
- The scan or fix job that dispatches this agent
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- scan-inventory ↗Checked
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-inventory.md
Supports: no shell, no vulnerability research, and directory ledger
- claude-security README ↗Checked
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/README.md
Supports: plugin install line
- Repository README ↗Checked
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/README.md
Supports: placeholder install line
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/LICENSE
Supports: Dependency setup and source-review boundary