skills/malue-ai/dazee-small/obsidian/Gen Agent Trust Hub

obsidian

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the obsidian-cli utility via a third-party Homebrew tap at yakitrak/yakitrak/obsidian-cli.
  • [COMMAND_EXECUTION]: The skill executes obsidian-cli commands to interact with the local file system for searching note content, managing file paths, and reading the vault configuration file at ~/Library/Application Support/obsidian/obsidian.json.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted Markdown data. 1. Ingestion points: The skill reads note content from the vault using the obsidian-cli search-content command. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are specified in the skill file. 3. Capability inventory: The skill can perform file system modifications including create, move, and delete operations via obsidian-cli. 4. Sanitization: There is no evidence of content sanitization or validation before the agent processes the note data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:20 PM