copywriting
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill is limited to text-based copywriting tasks.
- [DATA_EXPOSURE]: The skill instructions include reading project-specific context from files such as
.agents/product-marketing.mdand.claude/product-marketing.md. This is a standard pattern for providing domain-specific context to an agent and does not involve exfiltration or access to sensitive system credentials. - [PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety filters were found. The instructions are focused on the task of copywriting.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execution. It relies solely on the agent's internal language processing capabilities.
Audit Metadata