obsidian-memory-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily instructional, providing a architectural framework for note-taking and knowledge management. No malicious prompt injection or behavior override patterns were detected.
  • [SAFE]: The repository includes a scaffold script (scripts/scaffold_vault.py) that implements security best practices to prevent path traversal and symlink attacks. The reject_managed_symlink and canonical_vault_path functions ensure that files cannot be created or modified outside the intended Obsidian vault directory.
  • [SAFE]: The skill instructions and generated .gitignore file explicitly warn against and prevent the storage of sensitive information, such as .env files, SSH keys, or API credentials, within the Obsidian vault.
  • [SAFE]: External references and download links target the official GitHub repository of the author (atlasomnia) and trusted documentation sites for the Hermes platform, presenting no risk of remote code execution from untrusted sources.
  • [SAFE]: The skill utilizes standard system operations for file reading and searching, which are consistent with its stated purpose as a knowledge management extension.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:55 AM
Security Audit — agent-trust-hub — obsidian-memory-architecture