copywriting
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided copy drafts and read local context files like
.agents/product-marketing.md. This constitutes an indirect prompt injection surface where instructions hidden in the input could attempt to influence the agent's behavior. However, the risk is negligible as the skill's instructions are focused on text generation and do not utilize high-risk tools such as shell execution or network operations. - [EXTERNAL_DOWNLOADS]: The reference files include links to external research papers, GitHub repositories, and industry articles for attribution and documentation purposes (e.g., arXiv, ACL Anthology, and public marketing libraries). These links are informational for the user and do not involve automated fetching or execution of remote code by the agent.
Audit Metadata