Wiki Ingest
v0.1.0Ingest new source material into a persistent markdown knowledge wiki. Use when a user adds an article, note, transcript, report, paper, meeting summary, or o...
⭐ 0· 63·0 current·0 all-time
by@teki-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (ingest content into a markdown/git/Obsidian-style wiki) match the SKILL.md tasks (read source, update pages, index, log, links). There are no unrelated binaries, env vars, or config paths declared.
Instruction Scope
Instructions are limited to reading the provided source and updating wiki markdown files (index.md, log.md, topic pages). The SKILL.md assumes the agent has access to the wiki workspace and source files but does not hardcode any external endpoints or request unrelated system files. Recommend confirming what workspace path the agent will use (not specified) so it does not get access to unrelated files.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and arbitrary code execution risk.
Credentials
The skill requests no environment variables, credentials, or config paths. The actions it describes (reading and writing markdown in a wiki) do not require secrets; this is proportionate.
Persistence & Privilege
always is false and model invocation is not disabled (normal). The skill does not request permanent presence or attempt to modify other skills or system-wide settings.
Assessment
This skill is an instruction-only cookbook for updating a markdown wiki and appears coherent and proportionate. Before installing or enabling it for autonomous runs, confirm (1) which filesystem path will be treated as the wiki root so the agent has access only to the intended files, (2) whether the agent has network or VCS push permissions — if it can push commits or remote repos, consider restricting or auditing those credentials, and (3) run it on a copy of your wiki first so you can review changes (index.md, log.md, and page edits) before committing. There are no declared secrets or external downloads in the skill itself, and no scan findings, so the main operational risk is accidental modification of unintended files rather than malicious behavior.Like a lobster shell, security has layers — review code before you run it.
knowledge-managementvk975z315j5ewchs94zkgc6yyn184pv1dlatestvk975z315j5ewchs94zkgc6yyn184pv1dmarkdownvk975z315j5ewchs94zkgc6yyn184pv1dobsidianvk975z315j5ewchs94zkgc6yyn184pv1dwikivk975z315j5ewchs94zkgc6yyn184pv1d
License
MIT-0
Free to use, modify, and redistribute. No attribution required.