playwright-browser-evaluate
Warn
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill exposes the
browser_evaluatetool which accepts afunctionargument containing raw JavaScript code to be executed in the page context. This allows for arbitrary code execution within the browser sandbox. - [INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection because it interacts with external web content.
- Ingestion points: Untrusted data enters the context via page content processed by Playwright (SKILL.md).
- Boundary markers: None identified in the provided tool schema.
- Capability inventory: The skill can execute arbitrary JavaScript in the browser, which can be used to click elements, fill forms, or exfiltrate data from the page.
- Sanitization: There is no evidence of sanitization or sandboxing beyond the browser's own security model for the provided JavaScript strings.
Audit Metadata