copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for copywriting tasks and does not contain any executable scripts, shell commands, or binary files.
- [SAFE]: No network operations or external data fetching mechanisms were identified. The skill operates solely on context provided by the user within the chat environment.
- [SAFE]: The instructions include explicit safety and ethical guidelines, specifically prohibiting the fabrication of claims, statistics, testimonials, or guarantees.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided information about products and audiences. It mitigates potential instruction injection by implementing a mandatory 'Copy Brief Lock' phase, where the agent must summarize its understanding and wait for user confirmation before proceeding with copy generation. As the skill lacks dangerous capabilities like shell access or network requests, the risk associated with this surface is minimal.
Audit Metadata