semantic-labels

Pass

Audited by Gen Agent Trust Hub on May 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows standard instructional patterns for authoring USD metadata. It limits tool usage to Read and Grep for internal repository files. No exfiltration, obfuscation, or remote code execution patterns were detected.
  • [SAFE]: The skill targets specific internal paths within the repository (e.g., tests/docs/usd/data/) to resolve snippets. These files are used as reference material and do not involve untrusted user-controlled inputs or network downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
May 23, 2026, 03:11 AM
Security Audit — agent-trust-hub — semantic-labels