obsidian-plugin-vault

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from the Obsidian vault which could contain malicious instructions.
  • Ingestion points: The skill reads file contents and metadata in SKILL.md using this.app.vault.read(), this.app.vault.cachedRead(), and this.app.metadataCache.getFileCache().
  • Boundary markers: No explicit boundary markers or instructions to disregard instructions within files are provided.
  • Capability inventory: The skill allows for file system manipulation within the vault, including creation, modification, deletion, and renaming of files as documented in SKILL.md.
  • Sanitization: There is no evidence of sanitization or validation of the content read from the vault before it is processed.
  • [SAFE]: The skill includes documentation references to official Obsidian developer resources at docs.obsidian.md for API guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:45 AM
Security Audit — agent-trust-hub — obsidian-plugin-vault