obsidian-daily
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
obsidian-clitool to perform operations on local Obsidian vaults, such as opening daily notes, creating files, and searching for content. - [COMMAND_EXECUTION]: Uses system
datecommands (including GNU and BSD variants) to resolve relative dates like "yesterday" or "last Friday" into a standard format. - [PROMPT_INJECTION]: The skill processes data from external files (Obsidian notes) which presents a surface for indirect prompt injection.
- Ingestion points: Content is read from the vault using
obsidian-cli printandobsidian-cli search-contentas described inSKILL.md. - Boundary markers: No explicit delimiters or warnings are used when reading note content into the agent's context.
- Capability inventory: The skill can execute shell commands (
obsidian-cli,date,printf) which could be targeted by instructions found in note content. - Sanitization: No sanitization or validation of the note content is performed before it is processed by the agent.
Audit Metadata