chrome-devtools-e2e
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration suggests using
npxto download and run thechrome-devtools-mcppackage from the npm registry. This is a standard deployment method for MCP servers. - [COMMAND_EXECUTION]: The skill utilizes the
chrome-devtools-mcptool to perform browser automation, including script evaluation and element interaction. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests data from external websites.
- Ingestion points: Content is brought into the agent's context via
take_snapshot,list_console_messages, andlist_network_requests. - Boundary markers: No specific delimiters or "ignore instructions" guards are defined to separate untrusted page content from the skill's operational logic.
- Capability inventory: The skill grants the agent capabilities to
evaluate_script(running arbitrary JavaScript),clickelements, andfillform data, which could be abused if the agent follows instructions found within a page. - Sanitization: There is no evidence of filtering or sanitizing the data retrieved from the browser snapshot or console before processing.
Audit Metadata