typeset
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user content (Markdown, PDF, DOCX, etc.) to perform typesetting and humanization tasks.\n
- Ingestion points: File paths or raw text provided to the /typeset trigger.\n
- Boundary markers: The instructions lack explicit delimiters or safety prompts to prevent the agent from following instructions embedded within the source documents.\n
- Capability inventory: The skill performs file reading and file writing operations, and can execute the markitdown CLI tool.\n
- Sanitization: There is no mention of sanitizing or escaping the source content before it is processed by the agent.
Audit Metadata