meeting-notes-to-action-items
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a pure prompt template. It does not invoke any shell commands, perform network operations, or access sensitive local files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (meeting notes). While there is a risk that malicious instructions within notes could influence the generated summary, the skill only produces text for the user to review and does not automate any actions like sending emails or writing files.
- Ingestion points: Raw meeting notes and attendee lists provided by the user in the prompt template (SKILL.md).
- Boundary markers: The prompt uses natural language brackets to denote input areas but lacks explicit instructions to ignore embedded commands.
- Capability inventory: The skill is limited to text generation and formatting; no external tools, scripts, or system-level APIs are utilized.
- Sanitization: No input sanitization or validation is performed on the user-provided notes.
- [EXTERNAL_DOWNLOADS]: The skill contains a link to the author's official website (ootto.ai), which is a legitimate vendor resource and does not involve automated downloads or execution.
Audit Metadata