use-style

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use platform-specific commands such as open, xdg-open, or start to launch a local HTML file (examples/gallery.html) in the user's browser. This is a functional requirement to provide the user with a visual preview gallery of available styles.
  • [EXTERNAL_DOWNLOADS]: Several HTML example files included in the skill reference resources from established and trusted services:
  • Fetches the Chart.js data visualization library from the jsdelivr CDN.
  • Downloads typography assets from Google Fonts (fonts.googleapis.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill contains a mechanism to load custom style definitions from a project's .agents/styles/ directory. This design represents a potential surface for indirect prompt injection if an agent is used within a project containing malicious style files. The skill specifies the intended directory and file extensions to narrow the scope of this ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 02:29 AM