rig-characters

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is composed of markdown-based instructional documentation. It does not contain any executable scripts, shell commands, or obfuscated content.
  • [EXTERNAL_DOWNLOADS]: The skill references a robot model dataset hosted on HuggingFace (codepawl/menagerie-glb). This is a legitimate vendor resource used for rigging practice and does not introduce security risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingest user-provided rigging requests and project attachments.
    • Ingestion points: User requests, attachments, and project files (documented in SKILL.md).
    • Boundary markers: Absent.
    • Capability inventory: AI reasoning and instructions for 3D software tool usage. No dangerous system-level or network capabilities are exposed.
    • Sanitization: Absent. The risk is categorized as safe because the processed data is used for creative rigging tasks within a controlled software context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 12:28 PM