copywriting
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses entirely on providing linguistic and structural guidance for copywriting. All referenced files contain benign educational content and templates.
- [DATA_EXPOSURE]: The skill instructs the agent to read product-marketing-context.md files if they exist to gather necessary project context, which is a standard practice for AI agents and does not involve exfiltration or unauthorized access to sensitive system files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input for copywriting tasks. While this is an ingestion point for untrusted data, the skill lacks dangerous capabilities such as network access, arbitrary command execution, or file writes that could be exploited via injection.
Audit Metadata