Skills/ClawHub/macmini-knowledge-base

macmini-knowledge-base@1.4.8

CAUTION

Publisher claims: "⚠️ **本 skill 包含以下高危能力，使用前请仔细阅读 SKILL.md 顶部「⚠️ CAPABILITIES & RISKS」章节**： - Shell 执行 + 文件读写 + 安装 Homebrew 包（版本固定）+ 下载 Ollama 模型 - 修改 OpenClaw 配置 + 注册持久 cron 任务 + 飞书 webhook 推送 在 Mac Mini (M4) 上快速搭建本地知识库 + RAG 自然语言搜索系统。 适用场景： - 新 Mac 配置知识库：从零开始安装配置 Ollama、embedding模型、定时任务、文档解析 - 遇到 PDF 提取乱码、定时任务超时、skill 加载失败等问题 - 想要建立每日自动分析文档 + 08:00发送摘要到飞书的流程 - 迁移或复现知识库：打包整个 knowledge 目录和配置到新电脑 - **v1.4 新增**：CMap 残缺度自检（不预设来源）+ 50万字完整提取 + OCR fallback 到 .doc - **v1.4.8 新增**：4 项健壮性修复 1. **MuPDF/kreuzberg/OCR 异常不再静默吞掉**——记录到 stderr，保留错误信息 2. **[:3000] 硬截断修复**——使用 MAX_EXTRACT_LEN (500,000 字符)，长文档完整提取 3. **错误重试机制**——retry_with_backoff（2 次重试，指数退避 1s/2s） 4. **clean_noise 噪音清理**——3 阶段处理（行级 + span-based + disclaimer 公式专项），删除投行研报的"in whole or in part, to train or finetune"等版权/免责噪音 本 skill 会引导完成：目录结构创建、依赖安装、脚本部署、定时任务注册、OpenClaw 配置。 **v1.4.8 行为变化**： - PDF 提取失败时不再静默 return，错误信息写入 stderr（可查 /var/log 或 journal） - 长文档不再被截断到 3000 字符 - 临时性网络/IO 错误会自动重试 2 次 - 摘要文件不再包含"in whole or in part, to train or finetune..."等法律噪音 ⚠️ **重要：能力范围** 本 skill 不只是「搭建」，还包含： - 批量 OCR 修复（扫描 summaries/archives 找乱码 + 重新提取） - 目录归档清理（移动重复/孤儿文件到 .trash/） - 自动定时任务（23:00 分析 + 06:00 飞书推送） 使用前请仔细评估批量修改风险。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher seairteng · joined 11 days agoInstalls 1,721Last detonated 6d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-28 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Direct script execution from GitHub raw URL. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Outbound HTTP to raw IP addressSKILL.md:180 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/utils.py:335 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandSKILL.md:169 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/utils.py:543 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/utils.py:311 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/utils.py:298 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addressSKILL.md:180 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedSKILL.md:421 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/utils.py:495 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Direct script execution from GitHub raw URLscripts/setup.sh:83 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim seairteng: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim seairteng