auto-rig

Warn

Audited by Snyk on Aug 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The runtime workflow “forge_avatar” accepts user-supplied prompt/image_url(s) and then runs the Granite prompt-director + mesh generation + Make-It-Animatable auto-rig pipeline, meaning outsider-authored text (the prompt) is ingested by the LLM before any specific item selection.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 15, 2026, 04:15 PM
Issues
1
Security Audit — snyk — auto-rig