image

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes shell command templates for image optimization using utilities like cwebp, mogrify, and jpegoptim, as well as a curl command for site inspection. These are standard tools used appropriately for the skill's documented purpose.
  • [PROMPT_INJECTION]: The skill instructs the agent to ingest context from .agents/product-marketing-context.md. This is a standard practice for maintaining project context and does not include instructions to bypass safety guidelines or override behavior.
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known AI image generation APIs (Gemini, Flux, Ideogram) and design libraries (Satori, Vercel OG). These are informational references to established services and do not involve untrusted remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 10:15 PM
Security Audit — agent-trust-hub — image