browser-debugging

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the @anthropic/chrome-devtools-mcp package from the official NPM registry. This is a standard installation of a tool from a well-known developer.
  • [COMMAND_EXECUTION]: Instructs the user or agent to execute shell commands to launch Google Chrome with remote debugging enabled and to modify local configuration files like ~/.mcp.json.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external websites (such as console logs, network responses, and DOM structure), creating an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context through methods like devtools.get_console_logs, devtools.get_network_requests, and devtools.query_selector described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in the processed web data.
  • Capability inventory: The toolset includes browser JavaScript execution (evaluate_expression) and network monitoring, which could be exploited if malicious content is processed.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from web pages before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 05:43 PM
Security Audit — agent-trust-hub — browser-debugging