obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell utilities (find, grep) to search and locate Markdown files within a specific local directory path: /mnt/d/Obsidian Vault/AI Research/.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external note content which may contain instructions targeting the agent.\n
  • Ingestion points: Obsidian Markdown notes located in /mnt/d/Obsidian Vault/AI Research/.\n
  • Boundary markers: Absent; the content is read into the agent's context without delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The skill can read file contents (grep), search directory structures (find), and create/manage files as per the described workflows.\n
  • Sanitization: No validation or sanitization is performed on the content retrieved from the vault files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 06:43 AM
Security Audit — agent-trust-hub — obsidian-vault