browser-automation

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for creating agents that interact with and ingest data from untrusted external web pages via browser automation.
  • Ingestion points: Untrusted content enters the agent context through page.goto() and page.content() methods described in SKILL.md.
  • Boundary markers: The skill does not provide patterns for using delimiters or specific instructions to isolate the agent from malicious commands embedded in processed HTML.
  • Capability inventory: The documented patterns utilize network access to external domains and file system writes for saving screenshots and HTML data (e.g., fs.writeFile, page.screenshot in SKILL.md).
  • Sanitization: The instructions lack specific guidance on sanitizing or filtering external content before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 09:04 PM
Security Audit — agent-trust-hub — browser-automation