Auto Loop

v1.0.0

提供定时触发、任务调度、状态追踪及失败自动恢复的自动化任务调度功能。

0· 51·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
Crypto
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description, README, SKILL.md, and included source implement a local task scheduler (cron/interval/once, retries, persistence). Required artifacts (no env vars, built-in Node modules only) match the stated purpose.
Instruction Scope
SKILL.md gives scoped usage examples and config for scheduling tasks. It does not instruct the agent to read unrelated system files, contact external endpoints, or exfiltrate data. Handlers provided by the user are expected to run and may perform arbitrary work — the skill itself does not attempt broad data collection.
Install Mechanism
No install spec — instruction-only (with source included). No downloads or external package installs are declared, which is proportionate for a pure JS library using Node built-ins.
Credentials
The skill declares no environment variables, no credentials, and no config paths beyond creating its own state directory. There are no requests for unrelated secrets or cloud keys.
Persistence & Privilege
always:false and no special privileges. The code persists state under a local directory ('auto-loop-state') and writes JSON files — normal for a scheduler, but the skill will create and modify files in the agent's working directory.
Assessment
This package is internally consistent as a local Node.js scheduler. Before running: (1) review any task handler code you add — handlers execute arbitrary code and can access network/files; (2) be aware the skill creates a local 'auto-loop-state' directory and writes JSON state files in the working directory; (3) run the tests in a sandboxed environment first if you plan to use it in production; (4) if you allow the agent to invoke skills autonomously, ensure your policy for what tasks it may schedule/execute is constrained (autonomous invocation is allowed by default but not flagged here).

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

latestvk9753xwh6nf7aes3ej1w5ef53h84rdjm

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments