marketing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Data Exposure & Exfiltration (SAFE): The skill includes a specific requirement for the agent to check for sensitive data before creating visual content. It advises the user and agent to ensure no sensitive information is visible in screenshots from local development environments.
- Indirect Prompt Injection (LOW): The skill ingests product data to generate various marketing materials (social posts, emails, etc.). While a malicious product description could attempt to influence the generated output, the impact is limited to the text files being created and does not extend to system compromise or unauthorized tool execution.
- No Code (SAFE): The skill consists entirely of markdown-based instructions and folder structure templates. There are no associated scripts (Python, JS, etc.), configuration files for package managers, or commands that execute external code.
Audit Metadata