product-shots-main-image

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows secure development practices by delegating sensitive operations like API key management and image generation to a dedicated internal engine ('product-shots-image-gen').
  • [PROMPT_INJECTION]: The skill processes user-provided descriptions to formulate image generation prompts, representing a standard surface for indirect prompt injection common in creative tools. This is handled through structured templates and is considered a low-risk architectural pattern.
  • Ingestion points: user_request object in SKILL.md.
  • Boundary markers: Absent in the pseudocode prompt assembly logic.
  • Capability inventory: Invokes the product-shots-image-gen skill for image creation.
  • Sanitization: No explicit sanitization of user-provided strings is mentioned before interpolation.
  • [DATA_EXFILTRATION]: No network exfiltration, hardcoded credentials, or unauthorized access to sensitive file paths (such as SSH or AWS configurations) were found.
  • [REMOTE_CODE_EXECUTION]: No remote script downloads (e.g., curl|bash), package installations, or dynamic execution of untrusted code (e.g., eval/exec) were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 10:51 AM
Security Audit — agent-trust-hub — product-shots-main-image