the-save-desk
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, guiding the AI agent to design churn management systems (cancel flows, health scores, and dunning sequences) based on business context and provided playbooks.- [SAFE]: The skill includes a dedicated security reference (
references/agent-security.md) that provides explicit instructions to the AI agent on how to handle untrusted data. It mandates treating all fetched or pasted content as data rather than instructions, which is a key defense against indirect prompt injection.- [SAFE]: The security guidelines also explicitly prohibit the storage or echoing of credentials and require the agent to escape any interpolated content in emitted markup to prevent XSS.- [SAFE]: The skill enforces ethical constraints, prohibiting the use of protected personal categories (such as race, religion, or health status) for customer scoring or segmentation, even if that data is publicly available.- [SAFE]: No external code downloads, package installations, or remote execution patterns were detected.
Audit Metadata