obsidian-vault-manager
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process untrusted data from user-controlled Obsidian vaults.
- Ingestion points: The skill reads and refactors content from markdown notes (
.md), Obsidian Bases (.base), and Canvas (.canvas) files. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing the content of these files.
- Capability inventory: The skill allows the agent to search vault contents using
rg(ripgrep), read/write files, and manage vault paths via thescripts/vault_registry.pyscript. - Sanitization: No sanitization or validation logic is present to filter out potential malicious instructions embedded within the notes or metadata being processed.
Audit Metadata