design-with-images

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill defines a procedural workflow for visual design iteration using image generation and comparison tools.
  • [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting external visual content. 1. Ingestion points: UI surface captures and user-selected images (SKILL.md). 2. Boundary markers: None. 3. Capability inventory: Visual comparison and critique skills (compare-screenshots, screenshot-critique). 4. Sanitization: None. This ingestion surface is used for manual visual alignment and does not pose a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 02:29 PM
Security Audit — agent-trust-hub — design-with-images