skills/wenerme/ai/chrome-devtools/Gen Agent Trust Hub

chrome-devtools

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the use of "npx chrome-devtools-mcp@latest" to initialize the MCP server. This package is maintained by the well-known Chrome DevTools team.
  • [COMMAND_EXECUTION]: Includes the "evaluate_script" tool, which allows for the execution of JavaScript in the context of the browser page for advanced data retrieval and automation. This is a core feature of the intended functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the web, creating a surface for indirect prompt injection.
  • Ingestion points: Web page content is ingested via "take_snapshot" and "evaluate_script".
  • Boundary markers: None identified in the provided markdown.
  • Capability inventory: Includes browser control tools such as "evaluate_script", "click", "fill", and "navigate_page".
  • Sanitization: There are no documented sanitization steps for content retrieved from external websites.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 07:59 AM