glb-animation-handoff

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, specifically animation clip lists and scene plans, to generate structured documentation. This processing of untrusted data represents an indirect prompt injection surface.
  • Ingestion points: The skill reads clip names and scene plan details from external inputs as defined in the 'Operating procedure' of SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the external data being processed.
  • Capability inventory: The skill is documentation-only and explicitly restricts high-risk capabilities; the 'Official runtime boundary' section in SKILL.md states it does not export files, run Blender, or execute Python.
  • Sanitization: No specific sanitization or data validation logic is defined for the input scene plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:09 PM