explain-visually

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to create HTML artifacts that include Tailwind CSS via a Content Delivery Network (CDN) link. This is a standard and safe practice for styling web content.
  • [COMMAND_EXECUTION]: The workflow involves running a command-line tool named browser-verify to ensure the generated HTML artifact is responsive and free of layout issues. This is a functional requirement for the skill's purpose and is performed within the agent's execution environment.
  • [PROMPT_INJECTION]: The skill is designed to process external source material, which could theoretically contain malicious instructions. However, the risk is minimal given that the output is a specialized visual artifact (HTML/SVG) rather than executable system commands.
  • Ingestion points: External repositories, specifications, and pull requests provided as input material.
  • Boundary markers: Not explicitly defined in the prompt instructions to isolate untrusted content.
  • Capability inventory: The agent generates HTML/SVG code and executes a verification tool.
  • Sanitization: No specific sanitization or filtering logic is described for the input source material.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:52 AM
Security Audit — agent-trust-hub — explain-visually