Obsidian Vault Linker
v1.0.4Discover and write typed relationships between Obsidian vault notes. Uses plain Markdown and YAML — no plugins required. Works with any AI agent that has fil...
⭐ 1· 33·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (discover and write relationships between Obsidian notes) matches the SKILL.md: it reads Markdown files/frontmatter/wikilinks and can write Markdown/YAML links. It does not request unrelated credentials or tools.
Instruction Scope
Instructions correctly focus on vault files, frontmatter, tags, filenames and wikilinks and recommend using the Obsidian CLI if available. However, the instructions assume the agent has file-system access and include open-ended modes like 'look at this folder' and an optional autonomous mode that allows writing without per-link approval if the user explicitly grants it — this can be broad if the user points the skill at a non-vault or system folder.
Install Mechanism
No install spec or code is present (instruction-only), so nothing is downloaded or written by an installer. The only executable interactions suggested are optional use of an existing Obsidian CLI if present.
Credentials
The skill requires no environment variables, credentials, or config paths. File access to the vault is necessary for the stated purpose and is the only resource referenced.
Persistence & Privilege
always is false and the skill is user-invocable; model invocation is allowed (the platform default). Because the skill can write files (with user approval by default, or autonomously if explicitly permitted), granting it autonomous privileges or pointing it at broad filesystem locations increases risk.
Assessment
This skill appears coherent for linking Obsidian notes, but be careful with file access and autonomy: 1) Only point the skill to the specific vault folder you want processed (avoid root or home directories). 2) Keep the default workflow: allow it to read and report findings first, and only permit writes after you review them. 3) Avoid enabling 'run autonomously' unless you trust the agent and have backups of your vault. 4) If you have concerns, run it in a copy of your vault first to inspect what changes it proposes.Like a lobster shell, security has layers — review code before you run it.
latestvk97cfgw3kb413em3044sek697984tcq1
License
MIT-0
Free to use, modify, and redistribute. No attribution required.