aesthetic
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill describes workflows for capturing and analyzing screenshots from external inspiration sites (e.g., Dribbble, Behance). While this represents an untrusted data ingestion point, the risk is considered safe as the skill defines purely descriptive and documentation-based outcomes rather than automated execution of content found within the processed images. 1. Ingestion points: Inspiration sites via chrome-devtools in SKILL.md. 2. Boundary markers: Not specified. 3. Capability inventory: ai-multimodal for analysis, chrome-devtools for capture, media-processing for image editing. 4. Sanitization: Not specified.
- External Downloads (SAFE): References the use of gallery-dl for asset acquisition, which is a standard utility for the intended design research purpose.
- Command Execution (SAFE): Mentions bash and chrome-devtools as integration points for developer workflows. No hardcoded malicious command strings or obfuscated scripts were detected in the skill files.
Audit Metadata