behind-the-scenes-and-founder
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies external inputs such as comments, direct messages (DMs), and screenshots as material to be processed. It mitigates potential risks by explicitly instructing the agent to treat these inputs as content to be analyzed rather than commands to be executed.
- [DATA_EXPOSURE]: The skill includes a robust 'Transparency Tier' framework that strictly prohibits the disclosure of sensitive information, including customer data, personnel matters (firings/conflicts), legal issues, and security credentials. It also introduces a 'Permanence Test' to ensure all shared content is appropriate for public record.
Audit Metadata