user-guide
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the browser's
evaluatefunction to inject and execute Javascript code dynamically for the purpose of styling UI elements (e.g., adding outlines) before capturing screenshots. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the following factors:
- Ingestion points: Text content and labels are read directly from the browser DOM, and data is imported from external
flow-runnerortest-case-writerdocuments (SKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between instructions and data when processing these inputs.
- Capability inventory: The skill can execute scripts in the browser and trigger document generation (HTML, PDF, DOCX) through linked capabilities.
- Sanitization: There is no explicit requirement to sanitize or escape the labels and text extracted from the user interface before including them in the final output.
Audit Metadata