basic-workflow

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and code samples follow standard practices for using vendor-provided physics SDKs and do not contain any malicious patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a process for loading external scene data, which is an inherent part of its physics simulation purpose.
  • Ingestion points: USD file loading via ovstage.population.open_usd in SKILL.md.
  • Boundary markers: None; the data format is structured scene information rather than natural language.
  • Capability inventory: The skill uses the Shell tool for environment setup and code execution.
  • Sanitization: Standard for physics engine workflows; data is handled by native libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 11:53 AM