ClawHub

Backuptool

v2.0.4

Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Backuptool concepts, best practices, and implementation patterns.

⭐ 0· 136·0 current·0 all-time
byBytesAgain2@ckchzh
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
Name/description (Backuptool reference) match the provided assets: SKILL.md and a shell script that output static docs. There are no unexpected credentials, binaries, or external services required.
✓
Instruction Scope
SKILL.md says the commands output plain-text via heredoc with no external API calls; the included script only emits heredoc content and uses basic shell builtins (cat, echo). It does not read other files, environment variables, or call networked tools.
✓
Install Mechanism
No install spec is provided (instruction-only skill with an included helper script). Nothing is downloaded or extracted from external URLs during installation.
✓
Credentials
The skill requests no environment variables, no credentials, and the runtime script does not access env vars beyond local variables. No disproportionate secret access is requested.
✓
Persistence & Privilege
always is false (default). The skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed by platform default but combined with this skill's limited scope poses no additional risk.
Assessment
This skill appears to be a safe, local reference: it prints static documentation via a bundled shell script and does not access network or credentials. You may install it if you just want local reference content. Minor housekeeping notes: the SKILL.md, script, and registry list slightly different version strings (script VERSION=2.0.2, SKILL.md 2.0.3, registry 2.0.4) — not a security issue but worth noting. As best practice, review future updates or the upstream repo for any added network calls or credential usage before upgrading, and only enable autonomous invocation if you trust the skill's behavior in your agent environment.

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

latestvk973vz8gftcwyx9jhc1qpgmd7h83gpx9

License

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

Comments