email-nurture-planner
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill implements strong functional safety constraints, such as mandatory checks against a 'No Fly List' to ensure sensitive customer data is never included in the AI's output.
- [SAFE]: The skill includes explicit data freshness validation, requiring the agent to flag outdated marketing context (older than 6 months) or stale content (older than 18 months) to the user before proceeding.
- [SAFE]: The skill uses a structured, multi-step conversational process for gathering user input, which minimizes the surface area for direct prompt injection by limiting the scope of each interaction.
- [SAFE]: Integration with the 'Tiger Den' marketing platform is performed through scoped tool calls (e.g., get_marketing_context, search_content) rather than raw shell commands or direct network operations.
Audit Metadata