claude-video-image
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md's API Generation (Gemini 3 Pro Image) section explicitly says the generator "Uses Google Search for factual accuracy," indicating the agent ingests public web search results (untrusted third‑party content) that can influence generation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata