campaign-launch

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The instructions focus on establishing defensive operational gates and ensuring the user reviews all automated actions before execution.
  • [PROMPT_INJECTION]: The skill manages external data such as email templates and contact lists, which serves as a potential ingestion point for indirect prompt injection. This risk is mitigated by mandating a human-in-the-loop launch gate where the user must approve the literal text of messages.
  • [INGESTION_POINTS]: Message content added via sequence.add-step and contact data in enrollment.create.
  • [BOUNDARY_MARKERS]: Manual exact-text approval and mandatory verification of sequence state.
  • [CAPABILITY_INVENTORY]: Access to sequence.activate and enrollment.create operations.
  • [SANITIZATION]: Manual review of content is required before activation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:47 PM
Security Audit — agent-trust-hub — campaign-launch