obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior or high-risk patterns were detected.
  • [COMMAND_EXECUTION]: The skill uses find and grep for search operations within the local path /mnt/d/Obsidian Vault/AI Research/. These actions are restricted to the filesystem and are typical for note management.
  • [PROMPT_INJECTION]: There is an indirect prompt injection surface as the agent reads user-provided markdown content. This is a common property of tools that process external text data.
  • Ingestion points: Markdown files in the local vault read via grep.
  • Boundary markers: None provided in the workflow.
  • Capability inventory: Reading and writing local files via shell commands.
  • Sanitization: Note content is processed as plain text without sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — obsidian-vault