document-review
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill lacks safeguards against indirect prompt injection when processing untrusted document content.
- Ingestion points: Step 1 reads data from files provided by the user or found in the docs/ directory.
- Boundary markers: The skill does not implement delimiters or specific instructions to ignore embedded commands within the processed text.
- Capability inventory: The agent is empowered to read and update files based on the document content.
- Sanitization: No validation or sanitization of document content is performed before it is added to the model's context.
Audit Metadata