lookbook-curate

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or obfuscated content were detected in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill mentions downloading well-known machine learning models (DINOv2, CLIP, and InsightFace) during the first run. This is documented as expected behavior for its primary purpose of image curation.
  • [DATA_EXFILTRATION]: Network operations are restricted to local communications (e.g., localhost:8000) for tool orchestration, with no evidence of unauthorized data transmission to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 03:34 AM
Security Audit — agent-trust-hub — lookbook-curate