obsidian-vault

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard utilities like 'find' and 'grep' to search and organize notes within the designated '/mnt/d/Obsidian Vault/AI Research/' directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes the content of local markdown files, which represents an ingestion surface for untrusted data.
  • Ingestion points: The agent reads file content and filenames using 'find' and 'grep' as specified in 'SKILL.md'.
  • Boundary markers: The instructions lack explicit delimiters or guidance for the agent to distinguish between its core instructions and the content of the notes it processes.
  • Capability inventory: The skill provides instructions for the agent to execute shell commands to search, read, and create files.
  • Sanitization: No mechanism for sanitizing or validating the content found within the markdown notes is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 04:05 AM
Security Audit — agent-trust-hub — obsidian-vault