docs-cleaner
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted content from documentation files.\n
- Ingestion points: Documentation files are identified and read during the 'Discovery' and 'Value Analysis' phases (SKILL.md).\n
- Boundary markers: Absent; the instructions do not define delimiters or provide 'ignore instructions' warnings for the agent to use when parsing the content of external documentation files.\n
- Capability inventory: The agent is authorized to create new consolidated documents, update existing project files such as README and CLAUDE.md, and delete redundant source files (SKILL.md).\n
- Sanitization: Absent; there are no procedures mentioned for sanitizing or escaping the content read from documentation files before it is processed or used to influence file system actions.
Audit Metadata