skill-path-selector
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill is entirely composed of natural language instructions for a logical decision-making process.
- [DATA_EXFILTRATION]: There are no network operations, API calls, or commands that access sensitive files. The skill operates purely on the provided design checklist.
- [COMMAND_EXECUTION]: The skill contains no shell commands or subprocess calls. It explicitly states 'Do not write SKILL.md files,' preventing unauthorized file system modifications.
- [REMOTE_CODE_EXECUTION]: No external scripts or packages are downloaded or executed. The skill does not depend on any third-party software beyond the agent's core capabilities.
- [PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass safety filters or override system instructions. The 'Stop' and 'Human review' sections provide clear boundaries for the agent's autonomy.
Audit Metadata