cloudbase-document-database-in-wechat-miniprogram

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to "Then also read" companion reference files and provides standalone fallback raw URLs (e.g., https://cnb.cool/.../skills/cloudbase/references/...) which are public third‑party web pages the agent would fetch and interpret as part of its workflow, allowing external content to influence code/decisions.