Personal Deadline Radar
v1.0.0扫描个人待办、会议和消息摘要，找即将到期事项与时间冲突。；use for deadlines, calendar, tasks workflows；do not use for 自动改日历, 伪造截止时间.
⭐ 0· 93·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (deadline/calendar scanning) match the included artifacts: SKILL.md, resources templates, and a local Python script that produces structured reports. Required runtime is only python3 and no credentials or config paths are requested.
Instruction Scope
Runtime instructions are explicit: prefer producing a reviewable draft and, when available, run the provided local script (python3 scripts/run.py). The script reads files/directories and various text file types to build reports — this is consistent with auditing directories or inputs but means the skill can read arbitrary files the user points it at (markdown, code, CSV, etc.). Users should avoid passing broad roots (e.g., / or ~) if they don't intend wide file access.
Install Mechanism
No install spec or remote downloads; this is an instruction-only skill with an included local Python script. Nothing is written to disk by a package installer and no external dependencies are fetched.
Credentials
The skill requests no environment variables or credentials. The included script contains built-in detection patterns for risky snippets (e.g., curl|bash, rm -rf, secret-like tokens) but does not require or exfiltrate secrets.
Persistence & Privilege
always is false and the skill does not request persistent privileges or modify other skills. The script can write an output file if given an --output path (normal behavior) but the SKILL.md emphasizes read-only, review-first workflows.
Assessment
This skill appears coherent and low-risk: it runs a local Python script to analyze supplied inputs and produces reviewable Markdown. Before using it, do the following: (1) inspect scripts/run.py locally (it's included) and run the provided smoke-test in a sandboxed workspace; (2) do not point the skill at your whole home or root directory—supply only the calendar/todo files or a small directory to limit exposure; (3) avoid feeding sensitive tokens/passwords as input; (4) verify outputs before taking any automated action (the skill itself states it should not modify external systems). If you see network calls, unseen install steps, or requests for credentials in a future version, treat it as suspicious and re-evaluate.Like a lobster shell, security has layers — review code before you run it.
latestvk97d6yy6hy0c4xvxbd3m6kps4d836wv0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📡 Clawdis
OSmacOS · Linux · Windows
Binspython3