distill
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions provide a robust safety framework, specifically warning against the unauthorized execution of sensitive actions such as breaking public contracts, sending external communications, or accessing production data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external user requests which inherently introduces a risk of indirect prompt injection. However, the skill mitigates this by enforcing a rigid requirements structure (EARS syntax) and providing a 'verification' section that mandates objective, observable outcomes, which limits the potential impact of malicious instructions embedded in a request.
- [COMMAND_EXECUTION]: The skill performs repository inspection and file writing to a specific documentation directory (
docs/briefs/). These operations are standard for development-oriented skills and are conducted within the context of the agent's workspace.
Audit Metadata