granola-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill guides the agent to process and summarize untrusted external data from meeting transcripts and user-typed notes.
- Ingestion points: The agent ingests meeting transcripts and user notes during the enhancement and chat phases (SKILL.md, Step 5).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the transcript data.
- Capability inventory: The skill allows the agent to use Read, Write, and Edit tools to manage meeting notes and summaries.
- Sanitization: The skill lacks explicit sanitization or validation steps to ensure that content from the transcripts does not influence the agent's internal logic.
Audit Metadata