Skills
Navigate
skills/appautomaton/webmaton/chrome-devtools-cli/Gen Agent Trust Hub

chrome-devtools-cli

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the global installation of the chrome-devtools-mcp package via npm (npm i chrome-devtools-mcp@latest -g), which is a resource provided by the vendor 'appautomaton'.
  • [COMMAND_EXECUTION]: The skill relies on executing the chrome-devtools command-line utility for browser automation tasks such as click, fill, and navigate_page.
  • [DYNAMIC_EXECUTION]: The evaluate_script functionality allows for the execution of arbitrary JavaScript within the automated browser's context.
  • [INDIRECT_PROMPT_INJECTION]: As a tool that ingests external data from web pages and possesses powerful automation capabilities, this skill has an inherent attack surface for indirect prompt injection. 1. Ingestion points: Data enters the context via take_snapshot, list_console_messages, and list_network_requests. 2. Boundary markers: No specific delimiters are used to separate untrusted web content from agent instructions. 3. Capability inventory: High-impact capabilities include shell command execution and in-browser script execution. 4. Sanitization: The skill does not define methods for sanitizing data retrieved from external URLs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 05:09 AM