baoyu-image-gen

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external tools like curl and codex using safe APIs (execFileSync, spawn). These tools are used for handling API requests and image generation tasks, which is consistent with the skill's primary purpose.\n- [EXTERNAL_DOWNLOADS]: The skill connects to official, well-known AI service providers (OpenAI, Google, Azure, Replicate, etc.) to perform image generation and retrieve the results. These operations target trusted service domains.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes user-provided prompt files and concatenates them for API requests. However, this is inherent to the functionality of an image generation tool.\n
  • Ingestion points: User-provided strings via --prompt and file content via --promptfiles (scripts/main.ts).\n
  • Boundary markers: Absent.\n
  • Capability inventory: Network operations for API calls (fetch/curl) and file system writes to save images.\n
  • Sanitization: No significant sanitization is performed on the prompt text before transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:05 AM
Security Audit — agent-trust-hub — baoyu-image-gen