meeting-notes
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted external data (meeting transcripts) without boundary markers. While an attacker could embed instructions in a transcript, the skill has no system capabilities (such as file writing, command execution, or network access) to execute harmful actions. Evidence: 1. Ingestion: meeting transcripts; 2. Boundary markers: None; 3. Capabilities: None; 4. Sanitization: None.
- [No Code] (INFO): This skill contains only markdown instructions and no executable scripts or software dependencies.
Audit Metadata