deal-sourcing

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [Human-in-the-Loop Design]: The skill is designed with user oversight at every critical step, particularly before any external communication is initiated. Evidence: The workflow includes explicit notes like 'Never send emails without explicit user approval' and 'Always present the shortlist for user review'.
  • [Contextual Data Usage]: The skill uses tools such as Gmail and Slack to research context, which is a standard use of these capabilities for business development tasks. This helps ensure that outreach is relevant and informed by previous interactions.
  • [External Data Processing]: The skill processes information from external web searches to inform internal research and outreach drafting. (1) Ingestion points: Web search results (Step 1). (2) Boundary markers: The skill does not define explicit boundary markers for external data. (3) Capability inventory: Searching Gmail and Slack, and drafting emails in Gmail (Steps 2 and 3). (4) Sanitization: Relies on human-in-the-loop review as the primary security control.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 10:21 AM
Security Audit — agent-trust-hub — deal-sourcing