deepseek-integration

Warn

Audited by Snyk on Mar 10, 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). This skill directly calls the external DeepSeek API (https://api.deepseek.com/v1/chat/completions) and ingests its JSON/SSE chat completions in functions like generate_completion, generate_completion_stream, and the Tauri command generate_suggestions_stream (as shown in SKILL.md), so untrusted third‑party responses are read and can materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 12:25 AM