cohort-analysis

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script named churn-predictor.py to store analysis results and track longitudinal trends.
  • [DATA_EXPOSURE]: The skill reads brand-specific configuration and profile data from the ~/.claude-marketing/ directory to establish business context.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external CRM and Analytics MCPs, which represents a potential surface for indirect prompt injection.
  • Ingestion points: Customer acquisition data, transaction history, and engagement events are ingested from CRM and analytics platforms.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating external data into the agent's context.
  • Capability inventory: The skill possesses the ability to read and write to the local filesystem and execute Python scripts.
  • Sanitization: There is no evidence of data sanitization or validation being performed on the inputs received from external data sources.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 12:16 AM