kick-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and processes open Kick platform content — e.g., fetching chatroom IDs from https://kick.com/api/v2/channels/{slug} and handling webhook event payloads like "chat.message.sent" (described in SKILL.md and references/detailed-guide.md), which are untrusted, user-generated messages that the agent is expected to read and act on (moderation, automated responses), exposing it to indirect prompt injection.