chrome-devtools-cli
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
chrome-devtoolscommand-line utility for browser automation and management tasks. - [EXTERNAL_DOWNLOADS]: Documentation recommends the global installation of the
chrome-devtools-mcppackage from the npm registry to enable the skill's functionality. - [REMOTE_CODE_EXECUTION]: The
evaluate_scriptcommand allows the agent to execute arbitrary JavaScript code within the active browser page session. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to process data from external, potentially untrusted web pages. Ingestion points: Untrusted data enters the agent context through
take_snapshot(page content),list_console_messages(browser logs), andget_network_request(network traffic). Boundary markers: No explicit markers or instructions are defined to separate ingested web content from the agent's primary instructions. Capability inventory: The skill provides high-privilege tools includingevaluate_script,upload_file, and browser navigation commands. Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external sources.
Audit Metadata