NYC

profiling-tables

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from database tables which could contain malicious instructions designed to influence the agent's summary or next steps.
  • Ingestion points: SQL queries in Step 1 (metadata) and Step 5 (sample data).
  • Boundary markers: Absent in the SQL result processing instructions.
  • Capability inventory: Database access via the run_sql tool.
  • Sanitization: No explicit sanitization of database content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:48 PM