customer-success-manager
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill documentation describes a set of tools for processing customer health and churn risk data locally using standard Python libraries.
- [COMMAND_EXECUTION]: The instructions include command-line examples for running three local Python scripts (health_score_calculator.py, churn_risk_analyzer.py, and expansion_opportunity_scorer.py) on JSON input files.
- [NO_CODE]: The Python script source code was not included in the provided analysis package; the security evaluation is based on the usage patterns and descriptions within the SKILL.md documentation.
- [SAFE]: The skill ingests external customer data in JSON format for analysis. While this represents a theoretical surface for indirect prompt injection, the documentation describes a deterministic, algorithmic processing model rather than one that allows untrusted data to influence agent instructions or logic.
Audit Metadata