cli-anything-obsidian

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the cli-anything-obsidian Python package from an external registry. This is the core package for the skill and is maintained by the skill's author.
  • [COMMAND_EXECUTION]: The skill functions by executing the cli-anything-obsidian command-line utility, which interacts with the local Obsidian application and its file vault via a REST API.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads data from an external source (Obsidian notes) that could contain untrusted instructions. 1. Ingestion points: vault read command (SKILL.md). 2. Boundary markers: Absent; no specific instructions are provided to the agent to ignore instructions embedded in note content. 3. Capability inventory: vault create, vault update, vault delete, vault append, and command execute (SKILL.md) allow for file system modification and Obsidian command execution. 4. Sanitization: Absent; the skill does not specify any sanitization or validation of the content retrieved from notes before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:02 PM