browsh

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines instructions for invoking the browsh command-line utility to render web pages.
  • Evidence: browsh --startup-url https://google.com in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates browsing external websites, which creates an attack surface where untrusted web content could attempt to influence agent behavior.
  • Ingestion points: Web content rendered by browsh (SKILL.md).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Shell command execution for browsh and firefox (SKILL.md).
  • Sanitization: None specified; the skill relies on the underlying browser's rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:24 AM