awesome-openclaw-skills-zh

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows runtime flows that fetch and interpret third-party/user-generated content (e.g., Gmail/GoogleWorkspaceSkill reading messages, Apple Mail search_emails examples, and the custom_skill.process_inbox which calls fetch_emails then classifies and auto-acts like auto_reply), so the agent ingests untrusted external content that can drive decisions and actions.