SECURITY REVIEW / Anthropic
Scan redactor
Pins the Claude Security redactor that edits nothing unless the dispatch names three specific report files, and that tells itself not to repeat a secret in the reply.
“A scan-job redactor, not for direct invocation, that cleans three named report files or refuses with a fixed not-cleaned reply.”
01 / THE REASONING
Why this made the selection.
- The agents index has no entry for plugins/claude-security/agents/scan-redactor.md.
- The file states the required inputs as three labelled paths in one directory and a refusal line when that dispatch is absent, and it says the reply must not contain a value.
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-redactor.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 replaces credential values in a finished scan's report files with [REDACTED] and is not for direct invocation. Tools are Read and Edit.
- The body requires exactly three paths, jsonl, sarif, and report, in one directory, pointing at CLAUDE-SECURITY-RESULTS.jsonl, CLAUDE-SECURITY-RESULTS.sarif, and CLAUDE-SECURITY-RESULTS.md. Otherwise it says to edit nothing and reply with the fixed not-cleaned sentence.
- The reply is limited to a count plus a not-cleaned line when a file could not be finished, and it says never to write a value or any part of one.
- It reads every file fully before editing, handles JSON escaping and replaces longer values before substrings.
- It preserves JSON keys and file/uri/symbol fields, while treating hard-coded test-looking values and shortened secret fragments as candidates.
- 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 report file was opened or edited.
- The refusal sentence was not returned by a running agent.
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.
- Keep original reports access-controlled and separately scan final artifacts; a clean response is not a guarantee that no credential remains.
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-redactor ↗Checked
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-redactor.md
Supports: three-path refusal and no-value reply
- claude-security README ↗Checked
https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/README.md
Supports: plugin install line and best-effort redaction note
- 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