agent-browser

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the agent-browser utility via the npm registry and execute agent-browser install to download a Chromium instance.
  • [COMMAND_EXECUTION]: The core functionality of the skill involves executing local shell commands to automate browser actions such as navigation, form filling, and data extraction.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from the web.
  • Ingestion points: External web content enters the agent's context through agent-browser snapshot and agent-browser get text commands.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The skill allows the agent to interact with arbitrary websites, click elements, and fill forms based on the results of the snapshots.
  • Sanitization: No explicit sanitization or filtering of the web content is described before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 09:19 PM