e2e-ui-execute
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from project files which constitutes an indirect prompt injection surface.
- Ingestion points:
docs/e2e-ui/test-targets.md,playwright.config.ts, andpackage.json. - Boundary markers: Absent; there are no instructions to ignore or delimit embedded instructions in the source files.
- Capability inventory: The agent has capabilities for file system read/write and browser automation via Playwright MCP.
- Sanitization: Absent; the skill does not specify any validation or filtering of the ingested file content.
- [COMMAND_EXECUTION]: The skill dynamically generates Playwright test scripts and executes them based on the configuration and targets found in the project directory.
Audit Metadata