obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior or high-risk patterns were detected.
- [COMMAND_EXECUTION]: The skill uses
findandgrepfor search operations within the local path/mnt/d/Obsidian Vault/AI Research/. These actions are restricted to the filesystem and are typical for note management. - [PROMPT_INJECTION]: There is an indirect prompt injection surface as the agent reads user-provided markdown content. This is a common property of tools that process external text data.
- Ingestion points: Markdown files in the local vault read via grep.
- Boundary markers: None provided in the workflow.
- Capability inventory: Reading and writing local files via shell commands.
- Sanitization: Note content is processed as plain text without sanitization.
Audit Metadata