google-cloud-vision
Warn
Audited by Snyk on May 12, 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.md explicitly lists the "Detect Web Entities" action (under "Popular actions") which uses Google Cloud Vision to return related public web pages and images (open, user-generated content) as part of the action outputs that the agent is expected to read and can influence subsequent decisions or actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata