usd-copy-and-flatten

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to invoke standard, installed industry tools such as usdcat, usdchecker, and Blender CLI/add-on entry points. These are documented as dependencies for performing the skill's primary purpose.
  • [DATA_EXPOSURE]: The skill includes explicit instructions for security and privacy, requiring the agent to use the blender-sanitized-support-bundle tool to remove absolute paths, credentials, and restricted URLs before the handoff package is considered complete.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external 3D scene data and USD layers. It mitigates risks by requiring strict boundary markers (working in a unique, caller-owned directory) and performing validation steps (usdchecker) to ensure the ingested data does not contain unresolved or malicious paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 06:05 PM
Security Audit — agent-trust-hub — usd-copy-and-flatten