grilling
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any malicious code, obfuscated commands, or attempts to exfiltrate data.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to look up facts in the environment (filesystem, tools) in SKILL.md. This ingestion point lacks specific boundary markers or sanitization instructions, creating a surface for indirect prompt injection if environmental data contains malicious instructions. However, this is a standard capability for development-oriented agents.
- [EXTERNAL_DOWNLOADS]: A reference to a GitHub repository from a known community source is provided for attribution in NOTE.md, which does not involve runtime code execution.
Audit Metadata