add-line-channel

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

• Third-party content exposure detected (high risk: 1.00). The skill exposes the agent to arbitrary, untrusted user-generated messages received via the LINE webhook (e.g., the /line/webhook endpoint described in Step 2 "_handle_webhook" and the Cloudflare Tunnel webhook URL in the "Cloudflare Tunnel 設定" section of SKILL.md), which the agent is expected to parse and act on as part of its workflow.