browser
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/start.cjsuseschild_process.spawnto execute the Google Chrome binary on the local system. While this is the intended purpose of the skill, it allows the agent to initiate local processes. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Because it retrieves and processes content from external websites via
scripts/nav.cjsandscripts/pick.cjs, an attacker could place malicious instructions on a webpage that the agent might inadvertently follow when parsing the page content. - [REMOTE_CODE_EXECUTION]: The
scripts/eval.cjsscript enables the execution of arbitrary JavaScript within the browser context using theRuntime.evaluateCDP method. This capability allows for complex interactions with web pages but can be abused if the agent is manipulated into executing malicious code in an authenticated browser session.
Audit Metadata