copywriting-halbert
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-supplied artifacts such as copy briefs, primary copy jobs, and transactional copy. These ingestion points (SKILL.md) represent a surface where untrusted data enters the agent context. However, no specific dangerous capabilities (like network operations or code execution) are associated with this skill's instructions, and the processing of user-supplied text is central to its primary function.
Audit Metadata