generate-image

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Communicates with the OpenRouter API (openrouter.ai), a well-known service for accessing various AI models.
  • [COMMAND_EXECUTION]: Executes a localized Python script to facilitate image processing and API communication, which is expected for this utility.
  • [DATA_EXFILTRATION]: Reads user-specified image files and configuration from .env files for the purpose of transmission to the OpenRouter API. This behavior is consistent with the skill's documented functionality and relies on well-known service endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary text prompts which represent a surface for indirect instructions targeting the image generation model.
  • Ingestion points: The prompt argument in scripts/generate_image.py (referenced in SKILL.md) accepts external text.
  • Boundary markers: Absent; the prompt text is interpolated directly into the API request payload.
  • Capability inventory: The script performs network POST requests and local file system write operations.
  • Sanitization: No sanitization is performed on the user-provided prompt before it is sent to the remote model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — generate-image