tutorial-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE: No prompt injection or safety bypass attempts detected.
- SAFE: No network operations or data exfiltration patterns identified.
- SAFE: No third-party dependencies or remote script downloads.
- LOW (Indirect Prompt Injection): The skill instructs the agent to read
resources/implementation-playbook.md. This represents a potential surface for indirect injection if the content of that file is untrusted. However, the skill lacks any high-risk capabilities (e.g., command execution, internet access) that could be used for exploitation, resulting in a safe profile.
Audit Metadata