line

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests untrusted user-generated content via LINE webhook events and API calls (e.g., the "reply to a user event using a reply token received from a webhook event" and endpoints like /v2/bot/profile or /v2/bot/followers/ids), which the agent is expected to read and could materially influence subsequent actions such as sending messages or changing configurations.