browser-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill facilitates reading and interacting with external web pages, which can contain malicious instructions.
  • Ingestion points: Web page content, accessibility trees, console logs, and network traffic (SKILL.md).
  • Boundary markers: No delimiters or instructions are provided to distinguish untrusted web content from system prompts.
  • Capability inventory: The skill enables high-impact actions like clicking, typing, and capturing screenshots (SKILL.md).
  • Sanitization: No content validation or sanitization is mentioned.
  • [NO_CODE]: Absence of Scripts. The skill contains only usage instructions and metadata, with no executable code or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 10:40 PM