image

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill instructs the agent to read local context files, such as .agents/product-marketing.md, to gather information about the user's product. This is a standard practice for providing contextually relevant assistance and does not pose a security risk.
  • [COMMAND_EXECUTION]: The skill provides instructional shell command templates for image optimization using common system utilities like cwebp, mogrify, and jpegoptim. These commands are provided for legitimate marketing tasks and do not involve unauthorized access or dangerous parameters.
  • [SAFE]: External references to AI model providers and design platforms (including Google, OpenAI, Black Forest Labs, and Vercel) point to official documentation and well-known services. These are used neutrally to provide technical and pricing information to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:36 PM