browser-automation

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection because it ingests data from external websites that could contain malicious instructions.\n
  • Ingestion points: The skill uses tools like browser_snapshot, browser_get, and browser_network to read data from web pages.\n
  • Boundary markers: No delimiters or instructions are used to distinguish between system prompts and untrusted web content.\n
  • Capability inventory: The skill provides tools for network navigation (browser_navigate), script execution (browser_evaluate), and form interaction (browser_fill, browser_click).\n
  • Sanitization: There is no evidence of sanitization for the data retrieved from external URLs.\n- [COMMAND_EXECUTION]: The browser_evaluate tool allows the execution of arbitrary JavaScript. If the agent generates scripts based on content found on a website, it could lead to the execution of malicious code in the browser context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 06:59 AM