NYC

chatbot-analytics

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill explicitly defines prohibited data categories (PHI) and provides implementation patterns that ensure only anonymized metadata is stored. No hardcoded credentials or data exfiltration patterns were detected.
  • [Command Execution] (LOW): The skill metadata requests permissions for Bash (npm and npx). While these are powerful capabilities, they are contextually appropriate for a developer-oriented skill and no malicious commands or payloads are present in the documentation or code snippets.
  • [Prompt Injection] (SAFE): No instructions to override agent behavior, bypass safety filters, or reveal system prompts were identified.
  • [Indirect Prompt Injection] (SAFE): The provided TypeScript and SQL examples use secure coding practices, such as parameterized queries and derived metadata flags, which mitigate common injection risks during data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM