ClawHub

Feishu Leave Request

v1.0.1

Assist users in submitting leave requests via Feishu by collecting, confirming, and guiding through form completion and submission steps.

⭐ 3· 3.6k·18 current·18 all-time
by@baofeidyz
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and instructions describe submitting a leave request via Feishu desktop UI. The skill requires no credentials, no binaries, and no installs — which is coherent for a purely instructional helper that guides browser automation or asks for screenshots.
✓
Instruction Scope
SKILL.md stays on-topic: it collects only the leave fields (dates, duration, type, reason), requires explicit user confirmation before submitting, and gives navigation and error-handling guidance for the Feishu Approvals flow. It does mention using browser automation or screenshots but does not instruct reading unrelated files, environment variables, or sending data to third-party endpoints.
✓
Install Mechanism
There is no install spec and no code files. Being instruction-only means nothing is written to disk by the skill itself, which is the lowest-risk install model.
✓
Credentials
The skill declares no environment variables, credentials, or config paths — appropriate since it only guides UI interaction and does not need access to Feishu API keys or other secrets.
✓
Persistence & Privilege
The skill is not always-enabled and does not request persistent or elevated platform privileges. It does not modify other skills' configurations or ask for system-wide settings.
Assessment
This skill is an instruction-only helper and appears internally consistent, but note: it will ask you for personal leave details (dates, type, reason) so only share what you're comfortable disclosing. Do NOT provide Feishu/Lark login credentials into chat; if automation is used, it will need access to your desktop or browser — confirm and control that access. Prefer providing screenshots (with sensitive info redacted) if you do not want the agent to interact directly with your app. Because the skill's author is unknown and there is no install code, the direct code risk is low, but always verify any automated actions and watch for unexpected requests (e.g., asking for credentials or files unrelated to the leave request) before proceeding.

Like a lobster shell, security has layers — review code before you run it.

latestvk97adva08vc04xjzgawh7m92ts8046ee

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments