Junyi Family Knowledge Vault
v1.1.1Manages family knowledge by capturing raw notes, distilling insights by five dimensions, and organizing validated methods into a reusable Obsidian vault.
⭐ 0· 91·0 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
Name/description promise a local Obsidian vault writer and organization workflow; the included Python scripts and SKILL.md behavior align with that purpose (creating Inbox/Cognition/Guidebook files, scene classification, validation rules). There are no unrelated dependencies or credentials requested.
Instruction Scope
SKILL.md gives detailed rules and explicit triggers for capturing and classifying user content and instructs writing files to an Obsidian vault. This is within scope, but the many trigger phrases mean the agent may often propose saving user text — the agent will create/append files on disk when invoked. The instructions do not ask to read unrelated system files or to exfiltrate data.
Install Mechanism
No install spec — instruction-only plus two small Python scripts. There are no downloads or external installers. Risk is low because nothing is fetched from external URLs.
Credentials
No environment variables, credentials, or config paths are requested. The scripts operate on a user-specified vault path and enforce containment; requested permissions (file writes) are proportional to the stated purpose.
Persistence & Privilege
always:false (normal). The skill can be invoked autonomously by the agent (platform default) and will write files to the filesystem when used — this is expected for a vault-writing skill. Users should be aware that the agent needs permission to write to the chosen vault path.
Assessment
This skill appears coherent and focused on writing local Obsidian notes. Before installing, decide and confirm the vault path the skill will write into (run it on a test folder first), ensure the agent has only the intended filesystem permissions, and review/approve saves when the agent asks (because it triggers on many phrases). The included scripts already block absolute paths, path traversal, symlink escape, and disallow unsafe file extensions — still, consider running the scripts in a safe test vault to verify behavior before giving access to your primary notes.Like a lobster shell, security has layers — review code before you run it.
latestvk975f2m7ssb00q78n2jdcr63t183amgs
License
MIT-0
Free to use, modify, and redistribute. No attribution required.