obsidian-kb-artifacts
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include the use of a local
obsidianCLI tool to perform search, read, and append operations within the user vault. - [PROMPT_INJECTION]: The skill workflow involves reading and processing content from the Obsidian vault, which creates a surface for indirect prompt injection. 1. Ingestion points: Markdown notes in project directories (Sources, Knowledge, Experiments, Results) and JSON-based Canvas files. 2. Boundary markers: No delimiters or specific instructions are provided to separate untrusted file content from system instructions. 3. Capability inventory: The skill utilizes file system read/write permissions and CLI command execution. 4. Sanitization: No explicit validation or filtering of note content is defined.
Audit Metadata