skills/joelhooks/joelclaw/vault/Gen Agent Trust Hub

vault

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes tasks using the joelclaw CLI utility to manage file system interactions with the vault. Evidence: Defines a comprehensive command tree in SKILL.md for operations such as read, search, and audit.
  • [PROMPT_INJECTION]: The skill processes data from an external local directory (the Obsidian vault), which represents an ingestion surface for potential indirect prompt injection attacks. Ingestion points: Vault files accessed via joelclaw read and search commands (SKILL.md). Boundary markers: Absent. Capability inventory: Local command execution using the joelclaw CLI (SKILL.md). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 07:38 PM
Security Audit — agent-trust-hub — vault