new-policy
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: The skill takes policy names, purpose, rules, and exceptions directly from user messages (SKILL.md).
- Boundary markers: No specific delimiters or warnings are used to wrap the user-provided content in the generated markdown files to prevent downstream interpretation by an agent.
- Capability inventory: The skill uses file-writing capabilities to create
.mdfiles indocs/policy/anddocs/dev/policy/(SKILL.md). - Sanitization: There is no evidence of validation or sanitization of the user input before it is written to the filesystem.
Audit Metadata