obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use find and grep to interact with Markdown files in a specific local directory (/mnt/d/Obsidian Vault/AI Research/). This is a standard and expected functionality for a note management skill.
- [PROMPT_INJECTION]: The skill involves reading and processing content from external Markdown files, which inherently includes an indirect prompt injection surface (Category 8).
- Ingestion points: Note content is ingested into the agent's context through grep search results (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the notes.
- Capability inventory: The skill's capabilities are limited to searching and reading files using find and grep (SKILL.md).
- Sanitization: No explicit sanitization or validation of the ingested content is described.
Audit Metadata