multi-agent-image

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a template script (templates/linear_batch.py) that utilizes subprocess.run to execute local Python scripts for sequential image generation. This is a standard orchestration pattern used to chain internal skill components and does not involve shell-level execution of untrusted input.
  • [EXTERNAL_DOWNLOADS]: The skill performs legitimate network operations to download generated image files from the apimart.ai API. These operations use the official service endpoints required for the skill's primary functionality.
  • [DATA_EXFILTRATION]: Security analysis confirmed that sensitive information, such as the OPENAI_API_KEY, is managed via environment variables and only transmitted to the intended image generation service (apimart.ai). No unauthorized data transmission to third-party domains was observed.
  • [SAFE]: The skill implements robust multi-agent logic and local file management within its designated working directory (~/.hermes/agents/multi-agent-image/). All identified patterns are consistent with its documented purpose as a high-level image generation assistant.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 02:54 AM