godot-skills

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill's context7-auto-research sub-skill explicitly performs automatic web/document searches and uses "Context7 MCP" and "WebFetch MCP" to fetch online documentation and community best-practice content (e.g., "自动查询", /skill context7, and allowed-tools: WebFetch), so the agent will fetch and read untrusted public third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:01 PM