image

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides educational content and workflows for marketing image production. All external references target well-known and reputable services (Google Gemini, OpenAI, Vercel, Cloudflare, Canva, Figma).
  • [COMMAND_EXECUTION]: Includes benign command-line examples for image optimization using standard utilities (cwebp, mogrify, jpegoptim) and a curl example for auditing website image tags. These represent standard developer workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local context files (e.g., .agents/product-marketing.md) if they exist. This is a standard practice for context-aware agents and does not present an elevated risk in this implementation as the skill does not expose dangerous capabilities.
  • [EXTERNAL_DOWNLOADS]: Mentions the @vercel/og library for dynamic image generation, which is a package from a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 04:53 PM