obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions include shell command templates utilizing standard utilities like
findandgrepto perform file and content searches within a vault path defined by the user or local configuration. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for reading and searching external notes in an Obsidian vault, which serves as an ingestion point for untrusted data.
- Ingestion points: Search results and file content from Obsidian notes in
SKILL.mdworkflows. - Boundary markers: None specified in instructions.
- Capability inventory: Shell command execution (
find,grep). - Sanitization: Not specified; relies on the agent's internal handling of search results.
Audit Metadata