Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Obsidian CLI reference, but it exposes broad vault-changing and developer-level commands without enough scoping or confirmation guidance.
Install only if you want an agent to operate directly on your Obsidian vault. Before allowing commands, confirm the target vault and file, require explicit approval for permanent delete, publish, sync restore, plugin/theme changes, restricted-mode changes, JavaScript eval, and raw CDP commands, and prefer scoped read-only queries when possible.
The trigger phrases include broad everyday terms such as "obsidian," "vault," and especially "daily note," which can match ordinary user requests that are not clearly asking to invoke this skill. Overbroad routing can cause the agent to select a powerful automation skill unexpectedly, increasing the chance of unintended file access or modification in a user's vault.
The skill prominently documents destructive and privacy-affecting commands such as delete, permanent delete, move, read, search, and history/sync access without any explicit warning or confirmation guidance. In an agent setting, this makes accidental data loss or unintended disclosure more likely because the skill advertises high-risk operations as routine actions without guardrails.
No suspicious patterns detected.
