story-long-analyze

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). This is a GitHub repository referenced as the skill's source but hosted under an unfamiliar account (zenstory-ai); third‑party GitHub repos from unknown/low‑profile users can contain malicious code or installers, so treat downloads from it as potentially suspicious until verified.

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

• Third-party content exposure detected (medium risk: 0.30). 该技能在 Stage 1/2 会读取“用户提供的源路径/对话中贴出的小说文本”，并将原文分片后直接喂给子代理（chapter-extractor）进行情节点与摘要提取；因此外部用户可通过提交小说文本本身向运行时注入任意自由文本。