chrome-devtools-cli

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the chrome-devtools CLI to automate browser interactions and manage system tasks.- [EXTERNAL_DOWNLOADS]: The installation guide instructs users to install the chrome-devtools-mcp package globally from the NPM registry.- [DYNAMIC_EXECUTION]: The skill enables the execution of arbitrary JavaScript within the browser context through commands like evaluate_script and initialization scripts during navigation.- [INDIRECT_PROMPT_INJECTION]: Interaction with external web pages creates a surface for indirect prompt injection, as the agent processes untrusted content.
  • Ingestion points: The agent ingests external data through take_snapshot, list_pages, list_network_requests, and list_console_messages as described in SKILL.md.
  • Boundary markers: There are no markers or specific instructions provided to separate untrusted data from instructions for the agent.
  • Capability inventory: The tool possesses high-privilege capabilities including full filesystem access by default, network navigation, and browser script execution.
  • Sanitization: The skill documentation does not describe any methods for validating or sanitizing retrieved web content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:15 AM
Security Audit — agent-trust-hub — chrome-devtools-cli