image-generator
Warn
Audited by Snyk on Feb 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly includes an enable_web_search parameter (and a Tip: "Set enable_web_search: True to ground generation in real-world styles, brands, and visual references") which indicates it fetches and uses current public web data as input to image generation, exposing the agent to untrusted third-party content that could influence generation decisions.
Audit Metadata