copywriting
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates purely as a text generation guide for copywriting tasks, using internal markdown files for instructions and frameworks.
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read
.agents/marketing-context.mdto gather project information. While this file represents a point where untrusted data could enter the agent context, the skill does not use any tools with sensitive capabilities (such as network access or shell execution) that would make this ingestion risky. - [DATA_EXPOSURE_EXFILTRATION]: No evidence of hardcoded credentials, access to sensitive system paths, or network exfiltration logic was found.
- [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, dependencies, or commands that could lead to code execution.
Audit Metadata