Skills
skills/tentacle-pro/skills/tentacle-obsidian-init/Gen Agent Trust Hub

tentacle-obsidian-init

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script to scaffold the vault directory structure.
  • Evidence: scripts/init_vault.py is invoked via uv run to copy assets from assets/vault-scaffold/ into the current working directory.
  • [REMOTE_CODE_EXECUTION]: The documentation within the skill includes instructions for installing environment prerequisites using piped shell scripts.
  • Evidence: assets/vault-scaffold/.agents/skills/AGENTS.md provides shell commands like curl | bash for installing well-known tools such as Homebrew and Bun.
  • [EXTERNAL_DOWNLOADS]: The skill references several external installers from well-known and trusted technology providers.
  • Evidence: References include Homebrew (GitHub), Bun (bun.sh), and uv (astral.sh) for environment configuration.
  • [PROMPT_INJECTION]: The skill establishes operational rules for AI agents through specific markdown files.
  • Evidence: AGENTS.md files are designed to be read by AI agents to enforce folder conventions, naming standards, and execution rules within the vault workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 01:19 PM