LLM Wiki
v0.1.1Build and maintain a local Markdown knowledge wiki that compounds over time instead of relying on one-shot RAG retrieval. Use when the user wants to turn not...
⭐ 0· 0·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description match the SKILL.md workflow and the included Python scaffold. Required env vars/binaries/config paths are none, and the only code provided (init_wiki.py) creates a local vault scaffold — which is coherent with a wiki/second‑brain purpose.
Instruction Scope
SKILL.md instructs the agent to read, index, update, and maintain files inside a user-provided knowledge vault. This is expected for this purpose, and there are no instructions to call external endpoints or access unrelated system paths. The guidance is somewhat open-ended about what to ingest ("inspect new source material"), so operators should constrain the target directory to avoid accidental exposure of unrelated sensitive files.
Install Mechanism
No install spec (instruction-only) and no network downloads. The included script is a small local Python scaffold that writes Markdown files and directories; it does not fetch or execute remote code.
Credentials
The skill declares no environment variables, credentials, or config paths. Its runtime behavior (reading and writing files in the vault) is proportionate to its stated goal. There are no requests for unrelated secrets or service tokens.
Persistence & Privilege
always:false and user-invocable are set. The only persistent action is writing scaffold files into the user-specified target directory when the script runs. The skill does not request persistent global privileges or modify other skills/configs.
Assessment
This skill appears coherent and limited to local wiki maintenance, but take these precautions before installing or running: (1) review the init_wiki.py script (it only writes a scaffold) and SKILL.md for behavior you accept; (2) run the init script in a test directory first (do not point it at your home directory or other sensitive paths); (3) back up any existing notes before using --force; (4) if you grant an agent autonomy to run this skill, restrict its filesystem scope so it can only read/write the intended wiki directory; and (5) if you later combine this skill with other skills that have network access or credentials, be aware an agent could transmit wiki contents — consider least privilege for networked skills. If you want higher assurance, run the scaffold and keep the agent's access confined (container or dedicated directory) and inspect any changes before trusting them.Like a lobster shell, security has layers — review code before you run it.
latestvk978qy6y21h9farbcvnz1bdgv584a512
License
MIT-0
Free to use, modify, and redistribute. No attribution required.