discuss
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill defines a collaborative workflow for project planning and design exploration.
- [PROMPT_INJECTION]: The metadata contains an instructional constraint in the description field designed to manage when the agent activates the skill. This is a functional usage guideline rather than a malicious attempt to bypass safety filters or override system behavior.
- [DATA_EXFILTRATION]: The instructions permit the agent to read local codebase files to resolve design questions. This is a localized read operation necessary for the skill's purpose and is not associated with any network-based exfiltration triggers or commands.
Audit Metadata