gomtm-wiki-raw-write
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it reads and acts upon the content of user-provided documentation files in the
wiki/raw/directory. - Ingestion points: Document files located in the
wiki/raw/directory tree. - Boundary markers: The instructions do not specify any delimiters or safety markers to separate document content from agent instructions.
- Capability inventory: The skill involves file-writing capabilities to update the knowledge base.
- Sanitization: No sanitization or validation of the processed document content is mentioned.
- Mitigation: A robust mitigation is present in the requirement for human verification before any changes are committed.
Audit Metadata