ClawHub

Async Command

v1.2.1

Async command execution and progress reporting for OpenClaw agents. Use when running shell commands that take time (more than 5 seconds), and especially when...

⭐ 0· 64·0 current·0 all-time
by@guytogay
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the content: the SKILL.md explains how to start commands with exec(..., yieldMs=...), poll/log/kill via process(action=...), and manage background jobs. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
Instructions are narrowly focused on starting, polling, retrieving logs, and killing background processes. They do not instruct reading unrelated files, accessing environment variables, or sending data to external endpoints. They do rely on agent primitives (exec/process) which are expected for this feature.
✓
Install Mechanism
No install spec or code is included; this is instruction-only, so nothing is written to disk or downloaded.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The guidance does not reference any secret or external-service credentials.
✓
Persistence & Privilege
always is false and the skill is user-invocable. It does not request permanent presence or modify other skills' configs.
Assessment
This is a concise how-to for running long commands asynchronously using the agent's exec/process primitives. It appears coherent and low-risk, but remember: any mechanism that executes shell commands can run destructive operations — only grant the agent execution rights you trust. Confirm your agent implements the exec/process APIs described, and verify the stop/kill behavior in a safe environment. If anything in the SKILL.md (for example the referenced 'nek_stop' string) looks unfamiliar, ask the publisher for clarification before use.

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

latestvk97912jrawpa2883v9h6qtan65848k0b

License

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

Comments