sql-pro

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted SQL queries and database schemas from users, which are then processed by the agent.
  • Ingestion points: Untrusted SQL code enters the agent's context during the primary workflow for query optimization and schema analysis (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific isolation markers to prevent the agent from following instructions embedded within the provided SQL content.
  • Capability inventory: The skill explicitly instructs the agent to run 'EXPLAIN ANALYZE' and other maintenance commands like 'REINDEX' and 'VACUUM' (SKILL.md, references/optimization.md). In most SQL environments, 'EXPLAIN ANALYZE' executes the statement to generate actual performance metrics.
  • Sanitization: There are no recommendations for input validation or for running these queries in a restricted or read-only environment, which could lead to the execution of malicious data-modifying statements.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:50 AM
Security Audit — agent-trust-hub — sql-pro