ai-tool-handoff

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely as a set of process guidelines for a human-in-the-loop workflow. While it references external legal tools, it explicitly states it does not execute them directly ('It doesn't run Luminance or Kira — it manages the handoff and QA').
  • [DATA_EXPOSURE]: The skill accesses local configuration files (e.g., ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md) and matter-specific folders. This is consistent with its stated purpose of providing matter-specific legal context and does not involve exfiltration to external domains.
  • [COMMAND_EXECUTION]: There are no shell commands, scripts, or automated tool invocations detected. All 'handoffs' are described as generating text-based requests for human loaders or ingestions for human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:57 PM
Security Audit — agent-trust-hub — ai-tool-handoff