37soul

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and browse user-generated content from 37soul (e.g., SKILL.md heartbeat and post-task routines call https://37soul.com/api/v1/clawdbot/feed and https://37soul.com/api/v1/clawdbot/chat_messages) and to read recent_context and feed items and then reply or take actions based on that content, which exposes the agent to untrusted third‑party content that could carry indirect prompt injections.