obsidian-kb-artifacts
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process local Markdown notes and Obsidian Canvas (JSON) files, creating a surface for indirect prompt injection. * Ingestion points: The agent reads content from various vault directories including Sources, Knowledge, Experiments, and Results to perform formatting and synthesis. * Boundary markers: There are no specific instructions or delimiters defined to distinguish user data from agent instructions. * Capability inventory: The skill has the ability to write to the local filesystem and execute commands via the
obsidianCLI. * Sanitization: No explicit content sanitization or validation logic is described for the information read from the vault. - [COMMAND_EXECUTION]: The skill utilizes the
obsidianCLI tool for vault navigation, search, and note modification, which involves the execution of shell commands on the local system.
Audit Metadata