rig-characters

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate rigging method guide, but it tells the user to enable script auto-run for downloaded .blend rigs and Rigify generation, which weakens a protection beyond what the rigging task strictly needs, so it is sketchy rather than malicious.

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

  • Third-party content exposure detected (low risk: 0.10). The skill's runtime workflow reads the user's own mesh, files, and prompts plus first-party Blender/engine docs, and the only outsider-authored source is an optional community dataset (codepawl/menagerie-glb on Hugging Face) that the agent must actively choose to fetch for reference, which is a low-risk search/fetch path.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 12:27 PM
Issues
2