yy-anti-distill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract and write all REMOVE/DILUTE content "原文，保留完整上下文" into a private backup and to read files from disk, which requires including any secrets (API keys/passwords) verbatim in outputs.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill is explicitly designed to extract, aggregate and retain "core" proprietary knowledge from local/internal documents into a private backup (and can search local files), effectively facilitating unauthorized retention/exfiltration of employer intellectual property and aiding insider misuse.

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

• Third-party content exposure detected (high risk: 0.85). 该技能在运行时会读取用户指定的外部文档内容（如方式A/B/C/D读取的 work.md/persona.md/任意Markdown/TXT/PDF），这些文档正文会被用于步骤1-5的分类预览与清洗生成，从而作为“outsider-authored free text”进入LLM上下文；SKILL.md未限制这些输入必须由操作用户撰写。