browser-cdp
Fail
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to harvest sensitive authentication information and session data.
- In
SKILL.md, the documentation provides specific commands to extract authentication tokens fromlocalStorageanddocument.cookieusing browser evaluation tools. - The
setup-cdp-chrome.jsscript performs bulk copying of sensitive Chrome profile data to a new directory. This includes files such asCookies,Login Data(which contains stored passwords), andWeb Data. - [COMMAND_EXECUTION]: The
setup-cdp-chrome.jsscript makes extensive use ofchild_process.execSyncto execute system-level commands across different platforms. - On Linux and macOS, it executes
pgrep,pkill,ps,lsof,ss, andfuserto monitor and terminate processes. - On Windows, it utilizes
tasklist,taskkill,wmic, andpowershell(specificallyGet-NetTCPConnectionandGet-CimInstance) for similar process and network state management. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the automated processing of arbitrary web content. This creates a significant surface for indirect prompt injection, where malicious instructions hidden on a website could influence the agent's behavior while it is controlling the browser session.
Recommendations
- AI detected serious security threats
Audit Metadata