add-wechat

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

• Third-party content exposure detected (high risk: 0.90). The skill's adapter receives live, user-generated WeChat messages via Tencent's iLink API (see SKILL.md "typical-use: Long-poll" and the wiring flow that triggers on "first inbound message"), which are untrusted third-party inputs that the agent will read and act on (see scripts/wire-dm.ts and the "Wire your first DM" workflow).