agent-browser

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation for the agent-browser command-line tool, enabling web navigation and interaction tasks.
  • [PROMPT_INJECTION]: The skill facilitates ingesting untrusted content from external websites, creating an indirect prompt injection surface.
  • Ingestion points: Content is retrieved via snapshot and get text commands (SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified.
  • Capability inventory: The tool can navigate to arbitrary URLs, fill forms, and save session state (SKILL.md).
  • Sanitization: No sanitization or validation of the retrieved web content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 02:07 AM
Security Audit — agent-trust-hub — agent-browser