di-agent-query-optimization
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required runtime workflow can ingest outsider-authored free text when it calls
di-agent-query-substraitto generate a Substrait plan from the user’s natural language/query request; that natural language is free-form text not authored by the operating user (outsider input) and becomes LLM context for subsequent steps (SQL conversion and optimization).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata