x-chat-provider

Warn

Audited by Snyk on Apr 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs configuring XRequest to call arbitrary external endpoints (e.g., Step4 "Configure Usage" with XRequest("https://your-api.com/chat") and the OpenAI/DeepSeek examples) and the provider's transformMessage consumes streaming chunks from those third-party APIs, so untrusted external content is read and can influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 01:52 AM
Issues
1