closing-checklist

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads and writes to sensitive configuration paths (e.g., ~/.claude/plugins/config/claude-for-legal/). This is necessary for its stated purpose of maintaining deal-specific checklists and workspace context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documents (Sale and Purchase Agreements) and summaries to update the checklist. There is a potential risk that instructions embedded in these legal documents could influence the agent's behavior during extraction.
  • Ingestion points: Reads YAML checklists, legal agreements (SPA), and deal team summaries from the file system.
  • Boundary markers: Not specified; the skill relies on document structures and specific section titles within the legal documents.
  • Capability inventory: Reads and writes to specific project directories within the plugin configuration to store checklist state.
  • Sanitization: No explicit sanitization or validation of the ingested legal text is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:06 AM
Security Audit — agent-trust-hub — closing-checklist