webapp-testing
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
subprocessmodule to execute shell commands, specifically for starting local development servers (e.g.,npm run dev). While intended for local environment management during testing, the ability to spawn processes is a powerful capability. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web applications, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent retrieves untrusted content from the DOM and page source using
page.content()andpage.locator().all()inSKILL.md. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed web content.
- Capability inventory: The skill possesses capabilities for file system writing (screenshots), process execution (
subprocess.Popen), and further network interactions through browser automation. - Sanitization: The provided patterns do not include sanitization or validation of the text extracted from the web pages before it is processed or printed to the console.
Audit Metadata