70High
The skill introduces supply chain risk via an untrusted brew tap and is vulnerable to command injection from unsanitized user input.
Behavior Analysis
Description verified — behavior matches claim
Claims to do
Obsidian: Obsidian vault = a normal folder on disk.
Actually does
This skill uses the `obsidian-cli` tool to manage Obsidian vaults. It can set/print default vaults, search note names and content, create new notes, move/rename notes (updating internal links), and delete notes. It reads `~/Library/Application Support/obsidian/obsidian.json` to identify active vaults and utilizes Obsidian's URI handler for certain operations.
Skill Info
Namesteipete/obsidian
Registryclawhub
Version1.0.0
PURLpkg:clawhub/steipete/obsidian@1.0.0
Stars324
Downloads81,256
Installs2,373
Source
SHA-256dc45b522a0f0...
SHA-1fc8dd58373a0...
MD54520687795e6...
TLSH8041a7df778a...
Size2,334 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
ClawHubDocs
openclaw skills install steipete/obsidianAssessments (1)
AI Agent Traps ↗Supply Chain Risk via Custom Brew Tapmediumsupply chain
The skill installs 'obsidian-cli' from a custom 'brew' tap ('yakitrak/yakitrak'). This introduces a supply chain risk as the integrity of this third-party repository and the tool it provides cannot be guaranteed, potentially leading to the installation of malicious software.
100% confidenceline 5
install":[{"id":"brew","kind":"brew","formula":"yakitrak/yakitrak/obsidian-cli"Potential for Command Injection via obsidian-clihighcommand execution
The skill relies heavily on executing `obsidian-cli` commands. If user-provided input is directly passed as arguments to these commands without proper sanitization, it could lead to command injection, allowing an attacker to execute arbitrary system commands.
100% confidenceline 36
`obsidian-cli set-default "<vault-folder-name>"`, `obsidian-cli search "query"`, `obsidian-cli create "Folder/New note" --content "..."`
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/steipete/obsidian)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/steipete/obsidian"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/obsidian.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/steipete/obsidian.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow