skill-authoring-coach
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- Operational Focus: The skill is primarily instructional, guiding the agent on how to assist users in structuring their own Agent Skills. It does not utilize external tools, perform network requests, or access sensitive system directories.
- Safety Guardrails: The skill incorporates a review rubric and checklist that specifically directs the agent to identify and remove "secret leakage," "private paths," and "organisation-specific assumption" from the content it processes.
- Indirect Injection Surface: Although the skill is designed to process user-provided text (skill definitions), it does not possess exploitable capabilities such as file system writes, shell command execution, or network exfiltration that would allow for an indirect prompt injection attack to cause harm.
Audit Metadata