wrike

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-generated content from Wrike's public API (e.g., GET https://www.wrike.com/api/v4/tasks/<task_id>/comments and https://www.wrike.com/api/v4/folders/<folder_id>/comments), which the agent is expected to read as part of its workflow and could materially influence subsequent actions.