discussion-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of markdown instructions for the AI agent to follow when processing meeting transcripts. It does not contain any executable scripts, binaries, or automated installation steps.
- [SAFE]: The skill instructs the agent to work with local files in a user-specified directory (e.g.,
~/meetings/). There are no commands that attempt to access sensitive system directories, credentials, or hidden configuration files. - [SAFE]: No network operations or external data exfiltration patterns were detected. The skill specifically includes a best practice note advising users to keep sensitive meeting data local.
- [SAFE]: All references to third-party services (Granola, Zoom, Google Meet, etc.) are provided as informational documentation for the user on how to obtain their own transcripts, rather than automated integrations or dependencies.
Audit Metadata