blender-character-rig
Warn
Audited by Snyk on Nov 20, 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 reads mesh geometry, bone specs, and object and node names from a .blend or GLB the user supplies, which can be an outsider-made asset (e.g., a marketplace or downloaded file), so outsider-authored text such as names and custom properties could reach the agent only after it selects that file.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill documents an agent/MCP integration registration (
claude mcp add --scope userandcodex mcp add), which changes the supporting environment, but it shows no explicit irreversible operational loss, so the tier stays at low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata