aesthetic

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The 'Capture & Analyze Inspiration' workflow ingests data from external websites that could contain malicious instructions designed to influence the agent's behavior. * Ingestion points: Screenshots and site data from platforms like Dribbble, Behance, and Awwwards via chrome-devtools. * Boundary markers: Absent. The skill does not define clear delimiters or warnings for the agent to disregard instructions found within processed images/sites. * Capability inventory: chrome-devtools (browser control), ai-multimodal (LLM processing/image generation), and gallery-dl (file downloads). * Sanitization: Absent. No verification of external content is performed before analysis.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill references the use of gallery-dl to download reference images from external sources.
  • [COMMAND_EXECUTION] (LOW): The skill integrates with media-processing (FFmpeg, ImageMagick) and suggests bash execution for gallery-dl, involving standard command execution for media tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM