obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell utilities find and grep to interact with files in the local directory /mnt/d/Obsidian Vault/AI Research/ for its primary purpose of searching and organizing notes.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of markdown notes stored in the vault.
  • Ingestion points: Markdown files residing in the vault directory via find and grep commands.
  • Boundary markers: Absent; the skill lacks delimiters or warnings to prevent the agent from following instructions embedded within note text.
  • Capability inventory: Shell utilities (find, grep) used for traversing and reading the local filesystem.
  • Sanitization: No sanitization or instruction filtering is applied to ingested note content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:04 PM