tweet-style

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and analyzes public, user-generated X (Twitter) content via GET /styles/{username} on https://xquik.com/api/v1 (as shown in SKILL.md), and those untrusted tweets are read and fed into the agent's workflow (e.g., passed as context to write-tweets), so third-party content could indirectly inject instructions.