integration-management

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection Surface: The skill processes external artifacts such as purchase agreements, contract lists, and status reports. This creates a standard surface where the agent could encounter embedded instructions in data. To mitigate common risks associated with this, the skill includes a dedicated 'Formula injection defense' to sanitize output before exporting to CSV or Excel formats.
  • Data Access and Management: The skill reads and writes sensitive deal context and integration trackers within the local file system. This access is necessary for the skill's functionality as an integration management tool and is restricted to specific directory paths associated with the legal workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 12:40 AM