cat-check

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain any detected prompt injections, obfuscated code, or attempts to access sensitive system files.
  • [COMMAND_EXECUTION]: The skill instructions include shell commands that use uv run to execute a local tool located in the tools/glimpse directory. These commands are used to perform audits on Svelte components and capture screenshots of web pages. The commands use placeholders ({target_url}, {tenant}) for runtime parameters, which is the intended behavior for a UI testing tool.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to capture screenshots of external URLs via the glimpse tool. This is a functional requirement for its visual auditing process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:20 AM
Security Audit — agent-trust-hub — cat-check