obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions define workflows using find and grep to interact with a specific local directory: /mnt/d/Obsidian Vault/AI Research/. While standard for note management, these commands provide a surface for potential command injection if user-provided keywords are not properly escaped by the agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and searches content from external Markdown files, which could contain adversarial instructions designed to influence the agent's behavior.
  • Ingestion points: Markdown files (*.md) located within the vault at /mnt/d/Obsidian Vault/AI Research/.
  • Boundary markers: None identified; note content is processed directly through search tools.
  • Capability inventory: The skill uses find and grep for file discovery and content searching, and it describes workflows for creating notes and managing links.
  • Sanitization: No explicit sanitization, filtering, or validation of note content is described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:22 AM
Security Audit — agent-trust-hub — obsidian-vault