minto
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content to generate structural recommendations and HTML reports.
- Ingestion points: User-provided drafts, raw ideas, and conversation topics in the chat context (SKILL.md).
- Boundary markers: No instructions are provided to use delimiters or to disregard potential instructions embedded within the user's content.
- Capability inventory: The skill possesses the capability to write HTML artifacts to the user's local filesystem or workspace.
- Sanitization: The skill lacks instructions for sanitizing or escaping user-provided text before it is interpolated into the HTML delivery template, creating a potential for script injection in the generated file.
Audit Metadata