ClawHub

Linux

v1.0.0

Operate Linux systems avoiding permission traps, silent failures, and common admin mistakes.

⭐ 5· 2.8k·31 current·33 all-time
byIván@ivangdavila
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
The name and description match the SKILL.md content: a curated list of Linux pitfalls and diagnostic tips. No unrelated binaries, env vars, or services are requested.
ℹ
Instruction Scope
The instructions are purely informational and do not direct reading of unrelated files or secret state. They do mention real shell commands (e.g., docker system prune -a, tune2fs -m 1, rm -rf examples) that are potentially destructive if executed — the skill does not itself perform execution, but users/agents must not run those commands on production systems without review.
✓
Install Mechanism
No install spec or code files are present (instruction-only). Nothing will be written to disk or downloaded during install.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no disproportionate access requested for its stated purpose.
✓
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or modify other skills or system-wide settings. Model invocation is allowed (default), which is normal — nothing else in the skill increases privilege.
Assessment
This skill is an informational checklist and appears safe to install. It does not ask for secrets or install code. However, it references real shell commands and admin actions, some of which are destructive if run (e.g., docker system prune -a, tune2fs -m 1, rm -rf examples). Before letting any agent execute commands suggested by this skill, review them yourself and run them in a safe/test environment. If you are concerned about an agent acting autonomously, consider disabling autonomous invocation for the agent or requiring explicit user confirmation before running system commands.

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

latestvk974z0nnrjs02hg8wknkj1xb7h80v1q4

License

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

Runtime requirements

🐧 Clawdis
OSLinux · macOS

Comments