browser-automation

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and interact with data from external, untrusted web pages.
  • Ingestion points: External web content is retrieved through browser_query (using text, page_text, or list modes) and browser_snapshot as described in SKILL.md.
  • Boundary markers: The skill does not define explicit delimiters or instructions to treat browser-retrieved content as untrusted data rather than agent instructions.
  • Capability inventory: The skill utilizes powerful primitives including browser_navigate, browser_open_tab, and interaction tools like clicking, typing, and selecting elements based on queried data.
  • Sanitization: No sanitization, filtering, or validation of the content retrieved from the browser is mentioned in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:58 AM