page-cro
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE] (SAFE): The skill references a local file '.claude/product-marketing-context.md' to gather context. This is a common pattern for project-specific information and, since the skill has no network or file-writing capabilities, it presents no exfiltration risk.
- [REMOTE_CODE_EXECUTION] (SAFE): No scripts, executables, or package dependencies (Python or Node.js) were found in the skill files.
- [PROMPT_INJECTION] (SAFE): The instructions use standard expert role-playing for marketing tasks and do not attempt to bypass agent safety filters or override system instructions.
Audit Metadata