obsidian-cli
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the
obsidianCLI utility to perform file operations, search, and metadata management within a local vault. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files (the Obsidian vault) which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: Data enters the context via
obsidian read,obsidian search,obsidian daily:read, andobsidian template:readcommands (SKILL.md). - Boundary markers: There are no instructions for using delimiters or boundary markers when reading file content.
- Capability inventory: The skill has extensive write capabilities including
obsidian append,obsidian prepend,obsidian create,obsidian move,obsidian delete, andobsidian property:setacross all referenced commands (SKILL.md). - Sanitization: No sanitization, escaping, or validation logic is defined for processing vault content before it is used in subsequent operations.
Audit Metadata