granola-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill instructs the agent to share meeting summaries and action items via external integrations such as Slack, Notion, and Email. This behavior is the primary intended use case for the skill and relies on the user's existing configurations for these services.
- [PROMPT_INJECTION]: As the skill involves processing meeting transcripts (untrusted external data), it possesses an inherent surface for indirect prompt injection. A transcript containing malicious instructions could attempt to influence the agent's summarization or filing behavior, although the workflow emphasizes manual review and structured templates which mitigate this risk.
Audit Metadata