macos-agent-development

Fail

Audited by Snyk on Mar 10, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 0.90). This skill implements targeted UI surveillance and remote-control capabilities for WeChat via the Accessibility API (extracting and emitting message content and accepting stdin commands to inject text), which enables data exfiltration and impersonation and thus presents a high risk of deliberate abuse as a backdoor/spy agent.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's WeChatMonitor (WeChatMonitor.swift) explicitly reads user-generated chat text from the WeChat app via the Accessibility API (extractMessages/extractMessagesFromWindow) and forwards it to an orchestrator with MessageSender, so untrusted third‑party content from WeChat is ingested and can influence subsequent actions.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 10, 2026, 12:25 AM