automating-the-browser
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Documents the usage of the
crawlberg interactCLI tool for browser automation, including actions for clicking, typing, and scrolling. - [REMOTE_CODE_EXECUTION]: Documents the
executeJsfeature for running arbitrary JavaScript in the browser context, accompanied by a warning to use only trusted scripts. - [PROMPT_INJECTION]: The skill facilitates the ingestion of external web content, which represents a surface for indirect prompt injection. Ingestion points: The URL parameter in the
interactcommand. Boundary markers: No delimiters or specific warnings for the agent to ignore embedded instructions are provided in the documentation. Capability inventory: JavaScript execution, DOM extraction, and screenshot capabilities. Sanitization: The documentation does not specify any sanitization or filtering for the ingested web content. - [SAFE]: The skill promotes security best practices by explicitly advising users to avoid hardcoding credentials and instead use environment variables or secret management tools.
Audit Metadata