z-qa-browser
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The instructions direct the agent to utilize the project's Playwright runner and the host's browser tools to perform testing tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and process external content, such as application code and browser snapshots, creating a potential surface for indirect prompt injection. Ingestion points: Accesses application source code, test wrappers, and browser-generated snapshots (SKILL.md). Boundary markers: No specific delimiters or instructions to ignore embedded commands in the data are provided. Capability inventory: The agent can execute shell commands via the Playwright CLI and read/write files within the repository. Sanitization: No validation or sanitization of the external content is described.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation and repositories for the Playwright framework. Evidence: References to the Microsoft Playwright CLI on GitHub and the official playwright.dev documentation (SKILL.md).
Audit Metadata