product-photography

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the belt CLI tool for its operations, which is explicitly restricted in the frontmatter configuration (allowed-tools: Bash(belt *)). This follow the principle of least privilege.- [SAFE]: All command examples and documentation point to the vendor's own infrastructure (inference.sh) or well-known AI platforms (ByteDance and Fal.ai) for processing.- [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized data access was found. The instructions are transparent and consistent with the stated purpose of AI-assisted photography.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — product-photography