sales-expert
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and reference materials focus entirely on legitimate sales methodology and CRM business logic. No command execution, unauthorized network activity, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill defines data structures for ingesting lead and opportunity data (e.g.,
SalesCRM.create_leadinreferences/EXAMPLES.md). While this represents a theoretical attack surface for indirect prompt injection if the agent processes untrusted external sales data, the implementation follows standard business application patterns and lacks dangerous capabilities that would escalate this risk.
Audit Metadata