customer-success-manager
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external customer data files, which creates a potential vector for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The documentation describes tools that read from
assets/sample_customer_data.jsonor other user-provided JSON files. - Boundary markers: There are no explicit delimiters or "ignore instructions" warnings defined for the data ingestion process.
- Capability inventory: The skill utilizes three internal Python scripts (
health_score_calculator.py,churn_risk_analyzer.py, andexpansion_opportunity_scorer.py) to process data and generate health scores, risk tiers, and expansion recommendations. - Sanitization: The documentation does not specify any sanitization or validation logic for the input JSON data.
- [COMMAND_EXECUTION]: The skill requires the execution of local Python CLI tools to perform its core functions.
- Evidence: Multiple examples in the 'How to Use' and 'Scripts' sections demonstrate the execution of scripts via the
pythoncommand, such aspython scripts/health_score_calculator.py assets/sample_customer_data.json.
Audit Metadata