obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use find and grep commands to search for and manage markdown files. These operations are explicitly scoped to the local directory path /mnt/d/Obsidian Vault/AI Research/ and are consistent with the skill's stated purpose of note management.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads local markdown files from the vault, which constitutes a potential surface for indirect instructions.
  • Ingestion points: Local markdown (.md) files processed from the specified vault path.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for file content.
  • Capability inventory: Shell search commands (find, grep) and file system access.
  • Sanitization: No explicit validation or filtering is performed on search keywords or retrieved file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 08:31 AM
Security Audit — agent-trust-hub — obsidian-vault