engagement-matrix-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process feature usage data, MAU counts, and cohort metrics, creating a potential surface for indirect instructions embedded in processed data to reach the agent.
  • Ingestion points: Data enters the context via feature data lists passed to scripts/calculate_engagement_matrix.py and query results from scripts/extract_feature_usage.sql.
  • Boundary markers: The instructions lack explicit boundary markers or system-level directives to ignore instructions that might be contained within feature names or metadata strings.
  • Capability inventory: The skill's capabilities are restricted to mathematical analysis and reporting; it does not have the ability to execute shell commands, perform network operations, or modify the file system outside of its local scripts.
  • Sanitization: While the Python script strictly treats numeric fields as floats/integers for calculation, it does not validate or sanitize the feature names or string-based data used in the output reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:13 PM
Security Audit — agent-trust-hub — engagement-matrix-analytics