linkfox-aigc-imagegen

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The 'SKILL.md' file includes instructions explicitly commanding the agent to execute the generation script immediately upon receiving arguments, specifically forbidding the agent from waiting for user confirmation or further input. This attempts to bypass standard human-in-the-loop security controls.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts ('scripts/aigc_imagegen.py' and 'scripts/onboarding.py') to process image generation tasks and manage account onboarding.
  • [EXTERNAL_DOWNLOADS]: The 'aigc_imagegen.py' script includes functionality to download generated images from vendor-controlled URLs to the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:11 AM