table-video
Warn
Audited by Snyk on Nov 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow lets the agent search for and fetch external visual references (arbitrary web pages and images, saved to the project) when the user authorizes it, which is outsider-authored content the agent must actively seek out, so this is low rather than medium.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata