generate-image
Warn
Audited by Snyk on May 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly supports web grounding: SKILL.md documents an --grounding/--image-grounding option and scripts/generate.py (generate_image_async) constructs GoogleSearch/ImageSearch tools when those flags are set, meaning the agent can fetch open web/image search results and use that untrusted third-party content as context that can materially influence generation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata