盲区扫描——读昨天你与 AI 的全部对话，照出暴露的思维盲区（不是不懂的知识，是让某类真相一直看不见的思维习惯），再从微信读书挑一本书的一章精准补上，落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind', or wants yesterday's AI conversations analyzed for cognitive blind spots plus a targeted weread chapter to fill them. 可选参数：传一个日期(YYYY-MM-DD)扫那天而非昨天。NOT FOR 纵向深钻一个观点（用 ljg-think）、一个领域降秩（用 ljg-rank）、陪读一篇文本（用 ljg-read）、找一个领域的约束（用 ljg-constraint）。
Ask your Agent
Use this Skill: https://skilld.dev/gh/lijigang/ljg-skills/ljg-blind
This session only. Nothing lands on disk.
≈171 tokens on demand. Your agent reads this file only when SKILL.md points to it.
把微信读书 API 返回的裸 bookId、chapterUid 编码成电脑端可打开的网页阅读器链接。
bun "${HOME}/.agents/skills/ljg-blind/Tools/WeReadWebUrl.ts" <bookId> [chapterUid]--help 或 -h：显示用法并以退出码 0 结束。bun "${HOME}/.agents/skills/ljg-blind/Tools/WeReadWebUrl.ts" 573976 13输出：
https://weread.qq.com/web/reader/b2632d7058c218b269e80c0kc51323901dc51ce410c121bSource: SKILL.md on GitHub
The skill scans a user's AI conversation history to detect cognitive blind spots and recommends relevant book chapters from the WeRead platform. It contains a high-severity command injection vulnerability where a user-provided date parameter is directly interpolated into a shell command. Additionally, it accesses sensitive personal data, including the full history of AI interactions and private mission files.
No alerts
Risk: LOW · No issues
Signed by skilld at cbea579. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 19 hours ago.