weekly-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated notes and transcripts which can contain instructions that influence the agent.
- Ingestion points: Notes and transcripts retrieved via search tools in SKILL.md.
- Boundary markers: Absent; no instructions provided to delimit note content from agent instructions.
- Capability inventory: Retrieval of notes and transcripts; the agent context may include broader tool access.
- Sanitization: No explicit sanitization or filtering of external content is defined.
Audit Metadata