claude-plugin-guide
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local validation script 'bash brewcode/skills/skills/scripts/validate-skill.sh' and use 'rg --files' to locate manifest files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect instructions by processing external and local data.
- Ingestion points: Processes local repository manifests and fetches information from official Claude documentation at code.claude.com (SKILL.md).
- Boundary markers: No specific delimiters or safety warnings are provided for processing external data.
- Capability inventory: The skill allows the execution of bash scripts and file search tools (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering applied to ingested data.
- [EXTERNAL_DOWNLOADS]: The skill references official Claude documentation, including plugin and marketplace references, from code.claude.com.
Audit Metadata