sql-optimizer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied SQL queries to provide optimization advice, creating a potential surface for indirect prompt injection.
  • Ingestion points: User-provided SQL queries are ingested in Step 1 of the instructions in SKILL.md to determine the query text and context.
  • Boundary markers: The instructions lack explicit delimiters or instructions for the agent to treat the input query strictly as data to be analyzed rather than commands to be followed by the LLM.
  • Capability inventory: The skill utilizes database execution capabilities, such as EXPLAIN ANALYZE and metadata queries, to perform analysis as described in Step 1 and Step 2.
  • Sanitization: No explicit sanitization, validation, or filtering of the user-supplied SQL query is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:47 AM
Security Audit — agent-trust-hub — sql-optimizer