debug-browser-tests
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): No sensitive data access or exfiltration patterns detected. The code uses standard testing methods like screenshots and console log assertions.
- [Indirect Prompt Injection] (SAFE): The skill involves browser interaction (visiting URLs), which is a potential surface for indirect prompt injection. However, as documentation, it does not present a direct risk. Evidence chain: 1. Ingestion points: visit() calls to URLs. 2. Boundary markers: None. 3. Capability inventory: Browser navigation, screenshotting, and clicking. 4. Sanitization: N/A.
- [Remote Code Execution] (SAFE): No remote script downloads or dynamic code execution were found.
Audit Metadata