content-design-requests
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill incorporates a mandatory user approval step (Step 3) before any tasks are created or comments are added in Asana, maintaining human oversight of all automated actions.
- [SAFE]: All external interactions are restricted to the Asana platform via an authenticated MCP connector, with no data being sent to third-party or untrusted domains.
- [SAFE]: Sensitive identifiers and project configurations are retrieved from a local CONFIG.md file rather than being hardcoded, which aligns with secure configuration management practices.
- [SAFE]: The skill's data processing logic is focused on specific structural patterns (prefixes like '[Blog]') and does not execute untrusted content or scripts.
- [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found in the skill instructions or logic.
Audit Metadata