copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses entirely on copywriting guidance and does not include any executable code, shell commands, or network operations.
- [DATA_EXPOSURE]: The skill checks for the existence of
.claude/product-marketing-context.mdto inform its writing process. This is a localized read operation within the agent's workspace for gathering relevant marketing information and does not target sensitive system files or credentials. - [PROMPT_INJECTION]: The instructions establish a professional persona and set clear constraints for writing style and output format. There are no attempts to bypass safety filters, extract system prompts, or override agent instructions.
- [EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced for download or execution. All referenced files are local to the skill's repository structure.
Audit Metadata