skills/expo/skills/use-dom/Gen Agent Trust Hub

use-dom

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill identifies a surface where data flows from native code to a WebView and can trigger native actions via props. 1. Ingestion points: Component props such as code, id, pathname, and content shown in the examples. 2. Boundary markers: No explicit delimiters or boundary markers are used to isolate untrusted data. 3. Capability inventory: The examples demonstrate the ability to call native functions like showAlert and saveData from the web context. 4. Sanitization: No sanitization or validation of the input data is demonstrated in the provided code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:51 PM