documentation
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its interaction with documentation content.
- Ingestion points: Markdown files located in the agent/knowledge/ and agent/knowledge/harvested/ directories as specified in the README.md.
- Boundary markers: No explicit delimiters or instructions to disregard embedded commands in the documentation are provided.
- Capability inventory: The skill identifies capabilities for creating entries, rebuilding indices, and searching content, which involve file read and write operations.
- Sanitization: No sanitization, validation, or filtering logic for processed content is mentioned or implemented.
- [NO_CODE]: The skill consists of markdown-based instructions and metadata; no executable logic or functional scripts are provided in the scripts/init.py file.
Audit Metadata