performance-insights
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes business data and user-defined memories retrieved from external tools, which serves as a potential entry point for untrusted information.
- Ingestion points: Data is retrieved using tools such as
get_business_snapshot,query_metrics,get_pricing_context,get_listing,get_campaign_performance,get_inventory_alerts, andrecall_memoriesas defined inSKILL.md. - Boundary markers: There are no specific delimiters or instructions defined in the skill to distinguish or isolate instructions that might be embedded within the retrieved data.
- Capability inventory: The skill has the ability to record information using
save_memoryand display findings viapresent_metrics. - Sanitization: The instructions do not specify validation or sanitization procedures for the external data before it is processed or presented.
Audit Metadata