mcp-apps

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The skill documents an indirect prompt injection surface inherent to rendering external tool data in a UI. It effectively mitigates this risk by providing clear instructions and code snippets for XSS prevention and strict Content Security Policy (CSP) enforcement.
  • Data Exposure & Exfiltration (SAFE): The debugging and logging patterns provided are limited to local temporary files and do not involve unauthorized network transmission or sensitive credential exposure.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill references official and trusted documentation sources (Model Context Protocol) and does not contain patterns for downloading or executing untrusted remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 06:59 PM