use-style

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses platform-specific shell commands (open on macOS, xdg-open on Linux, and start on Windows) to open a local HTML file (examples/gallery.html). This is used as intended to provide a visual gallery of styles for the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files within the project's .agents/styles/ directory or the user's custom brain directory. This content is used to constrain the agent's code generation behavior. While this is an ingestion surface for untrusted data, it is the primary functional mechanism of the skill and is implemented without malicious patterns.
  • [SAFE]: The skill references font files from well-known and trusted domains (fonts.googleapis.com and fonts.gstatic.com) in its HTML examples. No other external network operations or dependencies were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 11:35 AM