art-photo-quiet-light

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several external photography-oriented websites and social media platforms for research and stylistic guidance in references/sources.md. These include established platforms like Instagram and Vogue, and are used solely as reference material without automated execution.\n- [PROMPT_INJECTION]: The skill processes user-supplied images and descriptions, creating a surface for indirect prompt injection. This is a standard risk for skills that analyze external data.\n
  • Ingestion points: User-provided images and text descriptions for photography planning and critique.\n
  • Boundary markers: None; there are no explicit instructions for the model to ignore instructions embedded in user-supplied reference content.\n
  • Capability inventory: The skill is limited to text generation and image-generation prompts; it lacks capabilities for file system access, network communication, or shell command execution.\n
  • Sanitization: None; external content is processed as-is for artistic analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 04:18 PM
Security Audit — agent-trust-hub — art-photo-quiet-light