Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
leetcode-plan
v1.0.112周LeetCode跳槽刷题计划助手。当用户输入"第X天"或"DX"时触发，返回对应题目；当用户提交解题答案或表示未解出时，生成错题记录并写入errorset.md；根据当天进度推荐复习之前的错题。适用于系统性刷题打卡、错题管理和间隔复习场景。
⭐ 0· 80·0 current·0 all-time
by八云绿@candiecandyy
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (12-week LeetCode plan,错题管理) match the provided files: references/plan.md contains the schedule and similarity table, SKILL.md describes using scripts/manage_errors.py to record/review errors. No unrelated credentials, binaries, or paths are requested.
Instruction Scope
SKILL.md instructs the agent to consult references/plan.md and to run scripts/manage_errors.py to add/review/list errors. The script only reads/writes errorset.md in the current working directory and reads references/plan.md for problem info; it does not access other system files or external endpoints. The SKILL.md explicitly warns errorset.md is created in the user's current working directory.
Install Mechanism
Instruction-only skill with a small Python script; no install spec, no downloads, and no archive extraction. Risk from installation is minimal — it requires a local Python runtime to run the script.
Credentials
No environment variables, credentials, or config paths are requested. The script uses os.getcwd() to decide where to write errorset.md — this is proportional to the stated goal of storing a local错题本.
Persistence & Privilege
always is false and the skill does not request persistent elevated privileges or modify other skills. Its only side effect is creating/updating errorset.md in the agent's current working directory.
Assessment
This skill appears coherent and limited in scope, but check the working directory before running it: it will create or overwrite errorset.md in whatever directory the agent runs in. Ensure you are comfortable with a local file being written there and that you have Python 3 available. Also avoid pasting sensitive data into '错误原因' fields since the skill stores user-provided text in the local errorset.md (the script does not transmit data externally). If you prefer the file elsewhere, run the agent from a directory you control or modify the script to point to a different path.Like a lobster shell, security has layers — review code before you run it.
latestvk9763wjbedat0tz6p0v5vp2a6d83jr2b
License
MIT-0
Free to use, modify, and redistribute. No attribution required.