← 返回 Skills 市场
xyc5872

PaperDaily

作者 xyc5872 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
340
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install paperdaily
功能描述
每日从 arXiv 计算机科学论文中筛选高价值文献推荐
安全使用建议
Before installing: (1) do not place real production Feishu App Secrets into node_modules/openclaw-paperdaily/.env until you review the package code; prefer storing secrets in a secure environment variable store or a .env in a controlled project root. (2) Ask the author for the source or the openclaw-paperdaily package code (or inspect the package from the npm registry) to confirm it only calls arXiv and Feishu APIs and does not exfiltrate data. (3) Verify that the Feishu app has minimal permissions and consider creating a dedicated test Feishu app for evaluation. (4) Prefer that the skill metadata declare required env vars and primary credential so reviewers and automated checks can see what secrets are needed. (5) If you cannot review the npm package, run the skill in an isolated sandbox and monitor network activity. If the package source proves benign (only arXiv queries and posting to Feishu), this assessment could be upgraded to benign.
功能分析
Type: OpenClaw Skill Name: paperdaily Version: 1.0.0 The skill delegates all core logic to an external dependency (openclaw-paperdaily) and requires sensitive Feishu API credentials (FEISHU_APP_SECRET). Most notably, SKILL.md instructs users to store these credentials in a .env file located inside the node_modules directory, which is highly irregular and could be used to obscure sensitive data from standard project audits. The lack of transparency in the external package combined with unusual secret management practices poses a significant risk.
能力评估
Purpose & Capability
The name/description match the actions described in SKILL.md (fetch arXiv CS papers, score and post recommendations to Feishu). Requesting Feishu credentials in SKILL.md is consistent with posting to a Feishu chat, but the repository metadata declares no required env vars or primary credential — that's an incoherence (the skill should have declared FEISHU_APP_ID/SECRET/CHAT_ID).
Instruction Scope
SKILL.md instructs running npm install and creating a .env with sensitive Feishu credentials inside node_modules/openclaw-paperdaily/.env. Asking users to place secrets inside node_modules is unusual and increases risk (files under node_modules are mutable by installs/updates). The instructions do not show what network endpoints the third‑party package calls, nor include the package code to inspect, so the agent would run code fetched from npm without full visibility.
Install Mechanism
There is no formal install spec in the registry, but package.json depends on openclaw-paperdaily from the npm ecosystem; SKILL.md explicitly tells users to run npm install. That means arbitrary code will be pulled from the public npm registry at install time — moderate risk because the dependency is not vendored and its source is not included in this bundle for review.
Credentials
SKILL.md requires FEISHU_APP_ID, FEISHU_APP_SECRET and FEISHU_CHAT_ID which are appropriate for sending messages to Feishu. However the skill metadata does not declare these required env vars (mismatch). Also instructing users to store the App Secret inside node_modules/.env is poor practice and increases the chance of accidental disclosure or exfiltration.
Persistence & Privilege
The skill is not always-enabled and does not request system-wide config. However installation writes files into the skill folder and node_modules (per SKILL.md). This creates persistent credentials stored alongside installed code and increases the impact if the fetched npm package contains malicious code. The skill does not request elevated platform privileges in metadata.
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 paperdaily
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /paperdaily 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
- 首发版本,自动筛选并每日推荐高价值 arXiv 计算机科学论文 - 支持通过「今日文献」及「刷新文献」触发获取推荐 - 评分综合论文新鲜度、关键词匹配与信息量,提升推荐质量 - 提供缓存机制,支持强制刷新 - 可自定义筛选关键词、时区和缓存时长 - 详细飞书集成与配置说明
元数据
Slug paperdaily
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

PaperDaily 是什么?

每日从 arXiv 计算机科学论文中筛选高价值文献推荐. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 340 次。

如何安装 PaperDaily?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install paperdaily」即可一键安装,无需额外配置。

PaperDaily 是免费的吗?

是的,PaperDaily 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

PaperDaily 支持哪些平台?

PaperDaily 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 PaperDaily?

由 xyc5872(@xyc5872)开发并维护,当前版本 v1.0.0。

💬 留言讨论