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-cli tool to perform operations on local Obsidian vaults, such as opening daily notes, creating files, and searching for content.
  • [COMMAND_EXECUTION]: Uses system date commands (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 print and obsidian-cli search-content as described in SKILL.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
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:44 PM
Security Audit — agent-trust-hub — obsidian-daily