obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides organizational guidelines and search workflows for a specific local directory path. It does not initiate network connections or include external code.
  • [COMMAND_EXECUTION]: The skill suggests the use of standard shell utilities like find and grep to manage files within the vault. These operations are restricted to the local environment and the specified vault path.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and search through external markdown files within the Obsidian vault. This constitutes a data ingestion surface where the agent could potentially encounter embedded instructions in note content. However, the skill acts as a standard file management utility and lacks complex automated triggers or exfiltration paths, resulting in a low risk profile.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 09:28 AM
Security Audit — agent-trust-hub — obsidian-vault