awesome-openclaw-tutorial

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 the agent fetching and processing arbitrary web and third-party content (e.g., "openclaw infer web 'https://example.com'", the content-approval flow that ingests webhook-submitted content and conditionally publishes to an external CMS, and the Feishu webhook example forwarding user messages), so untrusted public content is read and can influence actions/decisions.