The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The browser-use python command allows for the execution of arbitrary Python code within a persistent execution environment.
[REMOTE_CODE_EXECUTION]: The browser-use eval command enables the execution of arbitrary JavaScript within the browser context.
[DATA_EXFILTRATION]: The skill provides commands such as cookies export and profile sync that facilitate the extraction and synchronization of sensitive browser data, including session tokens and authentication cookies.
[COMMAND_EXECUTION]: The browser-use tunnel command allows for exposing local development ports to the public internet via Cloudflare's tunneling service.
[DATA_EXFILTRATION]: The browser-use screenshot command enables capturing visual data of the browser's current state and saving it to the local filesystem.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities.
Ingestion points: Processes untrusted external data from websites via the open and state commands.
Boundary markers: No specific boundary markers or 'ignore' instructions are provided for processed web content.
Capability inventory: Includes high-impact tools for Python execution, JavaScript execution, and network tunneling.
Sanitization: There is no evidence of sanitization or filtering of ingested web content before it is processed by the agent.

browser-use