NYC

image-gen

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill documentation recommends using an unverified 'Universal Installer' and cloning the skill from untrusted GitHub repositories. Evidence: README.md references https://github.com/AgenDev-Inc/skilz and https://github.com/SpillwaveSolutions/image_gen. These sources are not on the trusted organizations list.
  • COMMAND_EXECUTION (LOW): The skill is designed to run the 'imagen' CLI tool, which is an external, non-standard dependency. Evidence: README.md and CLAUDE.md provide examples of executing this tool. Executing unverified binaries from non-trusted sources poses a risk of arbitrary code execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:32 PM