Data Exfiltration URL in Skill Instructions

Detects SKILL.md files that instruct the agent to send data to external URLs, especially when combined with concealment language ("don't tell the user", "automatic", "verification step"). Legitimate skills may reference URLs for documentation, but they don't ask the agent to POST user data to them. Key pattern: instruction to send/post/upload + user data reference + URL.

建議回應

參考資料