sales-company-research
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- Controlled Execution Scope: The skill instructions explicitly forbid the agent from sending outreach, creating external drafts, or writing to CRM systems. This constraint ensures all outputs remain as drafts for user review, preventing unauthorized actions in external platforms.
- Sourcing and Attribution: The skill requires citing material sourced claims with useful links and labeling inferences clearly. This approach helps the user verify the accuracy of the gathered data and distinguishes between factual evidence and generated hypotheses.
- Data Ingestion Surface: The skill is designed to process data from external research and CRM systems. While this creates a surface for indirect prompt injection, the instructions prioritize evidence from authoritative sources and mandate that sourced facts be kept distinct from inferences.
Audit Metadata