controlled-generation

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill describes a legitimate workflow for image generation and restyling. It utilizes the vendor's infrastructure for processing images and generating outputs.
  • [EXTERNAL_DOWNLOADS]: The skill references images hosted on 'im.runware.ai', which is part of the vendor's own infrastructure for handling generated assets and preprocessor maps. This is standard behavior for this service.
  • [COMMAND_EXECUTION]: While the skill mentions calling tools like 'runware-run', it does so within the context of the platform's standard tool-calling interface for AI agents. No arbitrary or high-privilege command execution was detected.
  • [DATA_EXFILTRATION]: No patterns of sensitive data access or unauthorized exfiltration were found. The network operations involve sending user-provided images to the vendor's API for processing, which is the stated purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:08 PM
Security Audit — agent-trust-hub — controlled-generation