database-testing

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and analyze untrusted database schemas and SQL code snippets.
  • Ingestion points: External SQL code and schema definitions provided during testing and evaluation (documented in evals/database-testing.yaml cases tc001 through tc018).
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded natural language instructions within the data being analyzed.
  • Capability inventory: The skill utilizes sensitive capabilities including raw SQL execution (db.raw), transaction management, and agent-to-agent task delegation (Task).
  • Sanitization: No input validation or sanitization logic is specified for the code or data processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:25 AM