front-end-testing
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to install testing dependencies and Playwright browser binaries using the repository's package manager and the Playwright CLI.
- [EXTERNAL_DOWNLOADS]: The instructions mention downloading browser binaries via Playwright. As Microsoft is a well-known service provider, this download is considered safe for the intended use case.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed for auditing and testing front-end application code and DOM snapshots, which constitutes an attack surface for instructions embedded in the test subjects.
- Ingestion points: The agent analyzes application source code, UI templates, and rendered DOM content (SKILL.md, resources/playwright-e2e.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the application content being tested.
- Capability inventory: The skill makes use of package management and browser automation tools which could be targeted by injected instructions.
- Sanitization: No specific sanitization or filtering logic is described for handling instructions found within the code or UI being audited.
Audit Metadata