browser-verification

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing browser automation tools such as Playwright if not already available, which is a standard procedure for this functionality using reputable software.
  • [COMMAND_EXECUTION]: The verification process requires the agent to execute shell commands to start local servers and run browser automation scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with and analyzes external URLs, creating a surface where malicious web content could attempt to influence the agent's behavior.
  • Ingestion points: Web page content, console logs, and network data from target URLs specified in SKILL.md.
  • Boundary markers: No specific delimiters are used to isolate untrusted web content from the agent's instructions.
  • Capability inventory: The agent has shell access for environment setup and network access via the browser automation tool.
  • Sanitization: There is no evidence of content sanitization for data retrieved from browser sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:38 PM
Security Audit — agent-trust-hub — browser-verification