multi-ai-planning

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly recommends web research and optional use of multi-ai-research/Gemini CLI and Codex CLI (see "Prerequisites" and "Integration with Multi-AI Research") and instructs searching the web for best practices and GitHub examples, which means the agent will fetch and ingest open/public, user-generated content as part of its workflow—exposing it to potential indirect prompt injection.