← 返回 Skills 市场
Sf Scraper
作者
VenkataLokesh-dot
· GitHub ↗
· v0.1.0
403
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sf-scraper
功能描述
Scrape employee data from a logged-in SAP SuccessFactors browser session using browser automation. Use when: user provides an employee ID and wants employee...
安全使用建议
This skill does what it says — it uses the Browser Relay to read and interact with your logged-in SuccessFactors session. Before installing or enabling it: 1) Only enable it if you fully trust the skill owner and understand company policy about scraping employee data. 2) Be aware it can see anything in the attached Chrome profile (open tabs, cookies, session state). 3) Prefer to use it with explicit user invocation only (avoid allowing autonomous runs). 4) Test first on a non-sensitive/demo account to validate behavior. 5) Remove/disable the Browser Relay extension or detach the session when not actively using the skill. 6) If in doubt about legality or privacy, consult your security/privacy team before using.
功能分析
Type: OpenClaw Skill
Name: sf-scraper
Version: 0.1.0
The `sf-scraper` skill uses browser automation with full control over the user's authenticated Chrome session (`profile="chrome"`) to scrape sensitive employee data from SAP SuccessFactors. While the `SKILL.md` instructions explicitly state to avoid malicious actions and respect permissions, the dynamic construction of URLs (e.g., `targetUrl="{base_url}/sf/liveprofile?selected_user={employee_id}"`) and typing of user-provided input (`employee_id`) into web forms presents a high-risk capability. If the OpenClaw agent fails to sanitize these inputs before passing them to the `browser` tool, it could lead to client-side vulnerabilities like Cross-Site Scripting (XSS) within the user's browser session. This potential for exploitation through platform vulnerabilities, despite the skill's lack of explicit malicious intent, classifies it as suspicious.
能力评估
Purpose & Capability
The name/description (scrape employee data from an authenticated SuccessFactors browser session) matches the SKILL.md: all runtime instructions are browser snapshots/actions using an attached OpenClaw Browser Relay in Chrome. The declared requirements (none) are consistent because the skill depends on the live browser session and extension rather than environment variables or external binaries.
Instruction Scope
The SKILL.md explicitly directs the agent to use browser(action="snapshot"/"act"/"navigate") against the user's authenticated Chrome session and to navigate deep links, search, and admin pages. It does not call external network endpoints other than the user's SF instance. However, the instructions give broad capability to read and interact with any content in the attached browser session (including admin pages), and they do not constrain which fields are scraped or how results are returned — a genuine functional need but also a privacy/visibility concern for sensitive data.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low-risk from an install perspective because nothing is written to disk by the skill bundle itself.
Credentials
The skill requests no environment variables or credentials in its metadata. It relies on the user's authenticated browser session (via the Browser Relay extension) for access, which is proportional to the stated goal. There are no unrelated credential requests.
Persistence & Privilege
The skill is not marked always:true, which is good. Model invocation remains enabled (default), meaning the agent could invoke this skill autonomously; combined with the Browser Relay attachment, that would allow automated access to the user's active browser session. Autonomous invocation is platform-default, but users should be aware of the higher blast radius when a skill can interact with an authenticated browser without additional human confirmation.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install sf-scraper - 安装完成后,直接呼叫该 Skill 的名称或使用
/sf-scraper触发 - 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
v0.1.0
- Initial release of sf-scraper.
- Enables scraping of employee data directly from a logged-in SAP SuccessFactors session using browser automation—no API or OData used.
- Requires the user to have SuccessFactors open in Chrome with the OpenClaw Browser Relay extension active.
- Supports multiple navigation strategies to find employee profiles by employee ID, including deep links and UI search.
- Handles common loading scenarios including session timeouts, iframes, pop-ups, and lazy-loaded content.
- Extracts detailed employee profile fields such as name, email, department, manager, job information, and contact information.
元数据
常见问题
Sf Scraper 是什么?
Scrape employee data from a logged-in SAP SuccessFactors browser session using browser automation. Use when: user provides an employee ID and wants employee... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 403 次。
如何安装 Sf Scraper?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sf-scraper」即可一键安装,无需额外配置。
Sf Scraper 是免费的吗?
是的,Sf Scraper 完全免费(开源免费),可自由下载、安装和使用。
Sf Scraper 支持哪些平台?
Sf Scraper 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 Sf Scraper?
由 VenkataLokesh-dot(@venkatalokesh-dot)开发并维护,当前版本 v0.1.0。
推荐 Skills