ClawHub

Mychef

v2.0.3

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

⭐ 0· 115·0 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 (Mychef reference for devtools) matches the provided SKILL.md and the included script: both produce plain-text reference documentation. The only minor mismatch is metadata: registry version is 2.0.3 while the script sets VERSION="2.0.2" — a cosmetic inconsistency, not a security issue.
✓
Instruction Scope
SKILL.md explicitly states the commands output heredoc text with no external API calls; scripts/script.sh only prints local heredoc content and uses no network, credentials, or reads arbitrary system paths. No scope creep detected.
✓
Install Mechanism
There is no install specification (instruction-only skill). A single shell script is included but nothing in the bundle downloads or executes remote code during install.
✓
Credentials
The skill declares no required environment variables, no primary credential, and the script does not read environment variables or credentials. No disproportionate secrets or config access requested.
✓
Persistence & Privilege
always is false and the skill is user-invocable. It does not attempt to modify agent/system configurations or request permanent presence.
Assessment
This skill appears to be a harmless local reference tool: it includes a shell script that prints documentation and does not perform network calls or request credentials. Before installing or running, you may want to: (1) review the script (scripts/script.sh) yourself — it is short and readable; (2) note the minor version mismatch (metadata 2.0.3 vs script VERSION 2.0.2) and a small help-text substitution bug (the help heredoc is single-quoted so $VERSION won't expand) — both are non-malicious; and (3) as with any skill that contains executable scripts, only enable it in environments where running simple shell tools is acceptable. Overall risk is low.

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

latestvk974131mthctfc9y885jxs85gn83g7d8

License

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

Comments