Obsidian and OpenClaw Sync

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This skill is an instruction-only Obsidian sync guide whose local file-writing and context-mirroring behavior is disclosed and aligned with its purpose.

Install only if you want agents to write selected workspace knowledge into an Obsidian vault. Before mirroring USER.md, MEMORY.md, AGENTS.md, or similar files, confirm whether the vault is shared or cloud-synced and exclude secrets, private user data, and internal context you do not want preserved there.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly tells the agent to symlink a real Obsidian vault into the workspace and then write into it, but it does not require an explicit user confirmation before modifying external user files. That creates a real risk of unintended file changes, corruption of an existing vault structure, or writes into a shared/personal knowledge base outside the normal workspace safety boundary.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill recommends mirroring internal operating documents such as AGENTS.md, USER.md, MEMORY.md, TOOLS.md, and HEARTBEAT.md into a human-accessible Obsidian vault. Even though the text includes a brief privacy reminder later, it is not a strong, front-loaded warning and does not require sensitivity review, so it could expose secrets, internal instructions, personal data, or operational context in plaintext.

Ssd 3

Medium

• Confidence: 98% confidence
• Finding: Persisting agent memory and operating context into an Obsidian vault increases the chance that sensitive internal state or user-derived information becomes durable, discoverable, and editable outside the controlled workspace. In this skill's context, the danger is elevated because the vault is intended for both humans and agents, which broadens access and makes inadvertent disclosure more likely.

VirusTotal

63/63 vendors flagged this skill as clean.