obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions define workflows using
findandgrepto interact with a specific local directory:/mnt/d/Obsidian Vault/AI Research/. While standard for note management, these commands provide a surface for potential command injection if user-provided keywords are not properly escaped by the agent. - [INDIRECT_PROMPT_INJECTION]: The skill reads and searches content from external Markdown files, which could contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: Markdown files (
*.md) located within the vault at/mnt/d/Obsidian Vault/AI Research/. - Boundary markers: None identified; note content is processed directly through search tools.
- Capability inventory: The skill uses
findandgrepfor file discovery and content searching, and it describes workflows for creating notes and managing links. - Sanitization: No explicit sanitization, filtering, or validation of note content is described in the skill.
Audit Metadata