moai

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs agents to use WebSearch/WebFetch/Context7 and runs a Research/Explore agent that fetches external documentation and web resources as part of the required Phase 0 exploration (see workflows/moai.md "Agent 2
  • Research (subagent_type Explore with WebSearch/WebFetch focus)" and the Agent Selection Decision Tree), and those external pages are read and used to drive planning and implementation decisions—meeting the criteria for untrusted third‑party content that could inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 04:11 PM