business-pulse
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill primarily serves as a template and instruction set for an AI agent to query an internal CRM system (Epiphan AI MCP) using predefined tools like
weekly_briefandquery_dataset. - [DATA_EXPOSURE]: The skill uses real-world BDR IDs (e.g., 87486452, 423155215) and financial targets ($19.5M), but these are treated as internal configuration data for the agent's context rather than sensitive credentials or secrets.
- [REMOTE_CODE_EXECUTION]: No evidence of remote code execution or external package installation. The skill relies entirely on the host environment's integrated tools.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system prompts. It includes helpful guardrails reminding the agent to keep data internal and label derived fields as approximate.
Audit Metadata