gtm-role-descriptions
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured templates and authoritative benchmarks for revenue-focused job descriptions and compensation plans.
- [COMMAND_EXECUTION]: The skill includes a local Python validation script (scripts/check-output.py). Technical analysis confirms this script is limited to reading generated text files and applying regular expression checks for quality control. It does not perform network requests, access sensitive system paths, or execute arbitrary code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided role details to populate templates. While it lacks explicit boundary markers or sanitization for this data, the risk is negligible as the output is restricted to standard job description text and the accompanying validation script has no dangerous capabilities. Ingestion points: User-provided role details in prompts. Boundary markers: None explicitly defined. Capability inventory: Execution of scripts/check-output.py (file read only). Sanitization: None.
Audit Metadata