Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description ('core — core reference tool') matches the actual artifacts: SKILL.md describes static reference commands and the included script.sh emits only heredoc documentation. There are no unrelated requirements.
Instruction Scope
SKILL.md instructs the agent to output plain-text reference docs only; the provided script implements exactly that (no file reads, no network calls, no external endpoints, no access to credentials). There is no scope creep.
Install Mechanism
No install specification is present (instruction-only skill). This minimizes risk; nothing is downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths and the script does not reference any environment secrets. Requested access is proportionate to the stated purpose.
Persistence & Privilege
The skill is not forced-always, does not modify other skills or global agent config, and does not request persistent privileges. Autonomous invocation is allowed (platform default) but combined with the above, this poses no extra concern.
Assessment
This skill appears coherent and low-risk: it simply prints static reference documentation. Before installing, you may: (1) review the script locally (it's short and readable), (2) run it in a sandbox or restricted environment to confirm behavior, and (3) ensure your agent runtime prevents unexpected network access if you require strict isolation. Note: there are minor non-security bugs (e.g., help heredoc uses single quotes so $VERSION won't expand) but nothing indicating malicious behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk9719rqmy8xd99s5arhz1906t983e2n7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.