get-started
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill possesses a data ingestion surface by navigating to external websites using the chrome-devtools MCP. While this is a theoretical attack surface, the intended use case is for basic navigation and demonstration of a trusted tool.
- Ingestion points: External website content loaded into the browser context via chrome-devtools.
- Boundary markers: None provided in the skill instructions.
- Capability inventory: Browser navigation and page title/URL retrieval via chrome-devtools.
- Sanitization: None explicitly defined within the skill; relies on the agent's core safety mechanisms.
Audit Metadata