segment-anything-model
Warn
Audited by Snyk on Feb 16, 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 accepts and processes arbitrary, untrusted user-provided images (which may contain user-generated content) via the FastAPI endpoints (/segment/point and /segment/auto) and the Gradio input_image.select interface (and also uses GroundingDINO output/phrases), so the agent will read/interpret third‑party content at runtime.
Audit Metadata