written-consent

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • File System Access (Internal Configuration): The skill reads and writes to specific paths under ~/.claude/plugins/config/claude-for-legal/. This is the intended behavior for the skill to retrieve house resolutions, board compositions, and manage matter-specific workspaces as part of its legal workflow functionality.
  • Human-in-the-Loop Enforcements: The skill implements several hard-stop gates. For example, it prevents drafting if no house precedent is found and requires explicit user confirmation before proceeding with 'major one-off' actions or if the user is a non-lawyer. These are positive security controls that ensure user oversight.
  • Signatory and Conflict Tracking: The skill identifies and flags potential director conflicts and maps board members for signature blocks. This is used for generating the 'Signatory checklist' and 'Review prompts' to ensure corporate compliance.
  • State Law Compliance Research: The skill includes instructions to research and cite state-specific corporate statutes (e.g., DGCL) to verify notice requirements and signature validity, which is a standard part of the drafting process.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 12:39 AM