marketing-copy-editing
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any executable code, scripts, or binary files. It is composed of markdown instructions and a JSON evaluation file.
- [PROMPT_INJECTION]: The skill includes instructions to read context from external files such as
.agents/product-marketing.md. While this creates an indirect prompt injection surface where untrusted data could influence the agent's tone or messaging, the skill lacks dangerous capabilities (like network access, file writing, or command execution) to exploit this surface beyond influencing text output. - [EXTERNAL_DOWNLOADS]: No remote downloads or package installations are requested. References to external URLs are limited to documentation and source mirrors.
Audit Metadata