outline-first
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied materials like notes and drafts, creating a potential surface for indirect prompt injection.
- Ingestion points: User material, notes, and sources defined in the 'What to ask for' section of SKILL.md.
- Boundary markers: No boundary markers or delimiters are specified to separate untrusted user data from the agent instructions.
- Capability inventory: The instructions suggest saving content via tool calls to a connected notes app.
- Sanitization: No sanitization, escaping, or validation of user-provided content is performed.
Audit Metadata