← 返回 Skills 市场
sunyue1977

Pdf Smart Tool Cn 1.1.0

作者 SunYue1977 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
49
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install pdf-smart-tool-cn-1-1-0
功能描述
PDF智能处理工具 v2.1 | PDF Smart Tool. 支持PDF转换、OCR识别、合并拆分、数字签名、批量处理、水印添加、加密解密。触发词:PDF、转换、识别。
安全使用建议
This skill is an instruction-only spec with no source or homepage and contains internal inconsistencies (the SKILL.md lists required binaries but the registry metadata does not). Before installing or using it: 1) Ask the author/source for the concrete runtime implementation and where binaries/commands run (local vs remote). 2) Ask how digital signatures are performed — specifically where private keys/certificates are stored, whether they leave your machine, and how timestamps are obtained. 3) Verify the required binaries (pdftotext, tesseract, ghostscript) will be present and that Office conversions won't be sent to unknown external services. 4) Prefer testing in an isolated environment with non-sensitive documents. 5) If you need enterprise signing, insist on explicit handling of keys (hardware/keystore) and auditability. If the author cannot clarify these points or provide source/installation code, treat the skill as untrusted.
功能分析
Type: OpenClaw Skill Name: pdf-smart-tool-cn-1-1-0 Version: 1.0.0 The skill bundle contains only metadata and markdown instructions (SKILL.md and SKILL_v1.1.md) defining the behavior for a PDF processing tool. The requested dependencies (pdftotext, tesseract, ghostscript) are standard open-source utilities for PDF and OCR tasks. No executable code, data exfiltration logic, or malicious prompt injection attempts were identified.
能力评估
Purpose & Capability
The skill claims broad capabilities (PDF→Word/Excel/PPT conversions, OCR, digital signatures with CA certificates/timestamps, enterprise e-seals, encryption/decryption). The SKILL.md metadata lists required binaries (pdftotext, tesseract, ghostscript) which are plausible for OCR/text extraction and basic PDF work, but the registry-level summary provided to the evaluator lists no required binaries/envs — that's an internal inconsistency. Several advertised capabilities (high-quality Office format conversions, CA-based digital signatures, time-stamping, enterprise electronic seals, private deployment/API) normally require additional tools, libraries, cloud services, or access to private keys and certificate stores not declared here.
Instruction Scope
The SKILL.md is largely a user-facing feature spec and examples rather than concrete runtime commands; it does not instruct the agent to read arbitrary system files or contact external endpoints. However, it also does not specify how sensitive operations are performed (where signature keys come from, how uploads/downloads occur, where intermediary files are stored) — this omission creates ambiguity about handling of secrets and private artifacts.
Install Mechanism
There is no install spec (instruction-only), which is lower-risk for automatic code execution. Still, the embedded metadata declares required binaries (pdftotext, tesseract, ghostscript). If the runtime assumes those binaries exist, the agent may try to run them; because no install steps are provided, the skill relies on the environment. This is plausible but should be made explicit and consistent with registry metadata.
Credentials
The skill declares no required environment variables or config paths, yet features like '数字证书' (CA digital certificates), '企业电子签章' (enterprise e-seal), and time-stamps imply needing private keys, certificate files, or access to an external signing/timestamping service. The lack of declared env vars or config paths for key material is a proportionality gap: either the skill doesn't need keys (then how does signing work?) or it silently expects secrets to be provided via unspecified means. That ambiguity increases risk.
Persistence & Privilege
always is false and the skill does not request elevated persistence or automatic always-included behavior. It is user-invocable and allows autonomous invocation by default (normal). There is no evidence the skill modifies other skills or system-wide agent settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install pdf-smart-tool-cn-1-1-0
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /pdf-smart-tool-cn-1-1-0 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
pdf-smart-tool-cn-1-1-0 (v1.1.0) introduces major new features and enhancements: - 新增PDF转换功能:支持PDF与Word、Excel、PPT、图片等格式互转 - 增加OCR文字识别:支持多语言及手写体识别、表格结构识别 - 引入PDF合并、拆分及页面提取功能 - 增加数字签名支持,包括手写、电子、证书与时间戳签名 - 新增PDF加密、解密与权限设置 - 添加文字及图片水印功能,支持批量添加、删除 - 支持批量转换、加密/解密、水印等批量处理操作
元数据
Slug pdf-smart-tool-cn-1-1-0
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Pdf Smart Tool Cn 1.1.0 是什么?

PDF智能处理工具 v2.1 | PDF Smart Tool. 支持PDF转换、OCR识别、合并拆分、数字签名、批量处理、水印添加、加密解密。触发词:PDF、转换、识别。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 49 次。

如何安装 Pdf Smart Tool Cn 1.1.0?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install pdf-smart-tool-cn-1-1-0」即可一键安装,无需额外配置。

Pdf Smart Tool Cn 1.1.0 是免费的吗?

是的,Pdf Smart Tool Cn 1.1.0 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Pdf Smart Tool Cn 1.1.0 支持哪些平台?

Pdf Smart Tool Cn 1.1.0 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Pdf Smart Tool Cn 1.1.0?

由 SunYue1977(@sunyue1977)开发并维护,当前版本 v1.0.0。

💬 留言讨论