ClawHub

Copy

v1.0.0

Copy operations reference — file duplication, rsync patterns, CoW, buffer strategies, and cross-platform sync. Use when duplicating files, syncing directorie...

⭐ 0· 99·0 current·0 all-time
by@bytesagain1
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/description (copy/rsync/CoW reference) match the included SKILL.md and the bundled scripts. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
SKILL.md tells the agent to run scripts/script.sh with a small set of documented subcommands. The bundled script's visible code prints guidance text and examples rather than executing remote or system-altering operations. The instructions do not request reading unrelated files or exfiltrating data.
✓
Install Mechanism
No install spec is provided (instruction-only plus a local script). Nothing is downloaded or written to disk beyond the included script, so install risk is minimal.
✓
Credentials
The skill declares no required environment variables or credentials. SKILL.md documents an optional COPY_DIR variable (a harmless config), which is proportionate to the skill's purpose.
✓
Persistence & Privilege
The skill is not flagged always:true and uses default agent invocation settings. It does not request persistent system-wide changes or access to other skills' configs.
Assessment
This skill appears internally consistent and safe: it provides documentation via a bundled bash script and does not request credentials or external installs. Before enabling, quickly review the full scripts/script.sh to ensure there are no hidden commands beyond printed guidance (the provided portion only emits help text). If you allow the agent to invoke skills autonomously, remember that the skill contains shell examples (cp, rsync, dd, rm-like patterns in docs) — those are just examples, but avoid giving the agent untrusted inputs that could cause destructive file operations on your system. If you need stricter control, run the skill manually or in a sandboxed environment first.

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

latestvk977ejd63qarze07jtwwq7apmx83bhwa

License

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

Comments