churn-detection
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external data sources that may contain untrusted content, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: Processes support ticket sentiment, ticket history, and CRM account notes as specified in the 'Integration Points' section of SKILL.md.
- Boundary markers: The 'Output Format' and 'Intervention Templates' lack delimiters or explicit instructions to the agent to disregard instructions potentially embedded within the customer data.
- Capability inventory: The skill enables the agent to generate risk assessments and draft outreach emails based on the provided customer data.
- Sanitization: No sanitization, escaping, or validation measures are defined for handling content retrieved from external integrations before it is processed.
Audit Metadata