neo-clarification

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

• Third-party content exposure detected (low risk: 0.10). 本技能的執行流程僅要求讀取使用者當次送入的文字/截圖內容來做需求翻譯與澄清，並未包含主動搜尋或擷取任何外部（第三方）由他人投稿/發布的自由文本來源。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The SKILL.md explicitly instructs the agent at runtime to read and load external files that control its behavior: file:///Users/ben/Projects/neo-skills/skills/neo-clarification/references/5w1h-framework.md and file:///Users/ben/Projects/neo-skills/skills/neo-clarification/assets/clarification-template.md, which would be injected into the agent's context and directly influence prompts/instructions.