image
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a set of instructions and references for image generation and optimization. It contains no malicious code, obfuscation, or persistence mechanisms. External links point exclusively to well-known and trusted technology providers including Google, OpenAI, Vercel, and Cloudinary.
- [COMMAND_EXECUTION]: The skill provides standard shell commands for image optimization using common utilities such as
cwebp,mogrify,jpegoptim, andcurl. These are presented as educational examples for the user to perform tasks like batch conversion and checking image tags on a website. - [INDIRECT_PROMPT_INJECTION]: The skill instructions include a step to read local configuration files (e.g.,
.agents/product-marketing.md) to gather branding context. While this is an ingestion point for external data, it is a standard practice for personalizing agent behavior based on project-specific documentation and does not pose a significant risk in this context.
Audit Metadata