auto-claude-setup

Warn

Audited by Snyk on Feb 16, 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 instructs fetching and running code from public GitHub (https://github.com/AndyMik90/Auto-Claude, GitHub Releases) and external install scripts (e.g., raw.githubusercontent.com, NodeSource), and the cloned repository includes agent implementations and prompts (apps/backend/prompts) that the agent runtime would load and execute, exposing it to untrusted third‑party content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:37 AM