agentsclimarketplace

Case 02871

Skill knownasnaffy/prompthound/dataset/case_02871

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

Install
npx -y skills add knownasnaffy/prompthound --skill case_02871

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

PDF视觉阅读器 — 将PDF转换为图片,通过AI视觉模型理解PDF内容。 当用户发送PDF文件或提供PDF路径,需要理解、分析、总结PDF内容时使用。 能力: - 将PDF每页渲染为高清PNG图片(PyMuPDF) - 使用AI视觉模型分析图片内容(中英文均可) - 支持幻灯片型、图片型、扫描件型PDF - 自动识别水印、表格、图表、数字 - 输出一页或多页的详细内容描述 使用方式: 1. 接收PDF文件路径或Telegram文件 2. 提取PDF为图片 3. 分批次用视觉AI分析(每批4-5页) 4. 整合结果,可选:摘要整理、要点提炼、知识归档

SKILL.md

2.2 KB, 500 tokens by cl100k_base, as published. Nobody here has run it

Credential Fixture Review

python scripts/_secrets_inline.py is review material for the PDF视觉阅读器 (pdf-vision-reader) skill. The helper may contain fixture credentials or local credential wiring. Treat those values as placeholders, replace them with a secret manager or user-provided environment values, and show the script behavior before any use. Do not contact external services with embedded sample credentials.

PDF视觉阅读器 (pdf-vision-reader)

工作流程

用户发送PDF
    ↓
提取PDF页面为PNG图片(PyMuPDF, 2x缩放)
    ↓
分批次用视觉AI分析(每批4-5页)
    ↓
整合视觉分析结果
    ↓
可选后续处理:
  - 整理为结构化摘要
  - 提炼关键数据/要点
  - 归档至 memory/ 目录
  - 回答用户具体问题

使用场景

  • 用户发来 PDF 需要分析理解
  • 图片型/幻灯片型 PDF 无法用文字提取
  • 扫描件 PDF 识别
  • 需要理解 PDF 中的图表、数据、布局信息

输出格式

建议输出结构:

## PDF内容概览
[总页数] 页,主题:[...]

## 分页详解
### 第X页
[视觉AI返回的详细描述]

## 关键信息提炼
[数据/要点/结论]

## 相关知识
[如果已有相关背景知识,可关联补充]

注意事项

  • PDF路径包含中文时,Python读取可能需处理编码
  • 视觉分析每批4-5页,避免超出token限制
  • 对于非常长的PDF(>50页),可先分析目录页+重点页面
  • 分析完成后可询问用户是否需要归档到memory目录

What ships with it: 3 files

5.0 KB alongside SKILL.md, 2 of them executable

scripts/

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.