poteto-help
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a documentation and navigational guide for the 'pstack' toolset, mapping user queries to relevant sub-skills and documentation pages.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was detected.
- [SAFE]: The skill's configuration explicitly disables model invocation (disable-model-invocation: true), which minimizes the attack surface by preventing the agent from autonomously executing code or making calls while in help mode.
- [SAFE]: External references are limited to local files and directories within the expected repository structure, such as references/prompting.md and references/recipes.md.
Audit Metadata