di-agent-flow-pushdown-optimizer
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow ingests DataStage flow code retrieved via
retrieve_datastage_flow_code(outsider-authored issue/PR/wiki/thread–like content category), and then passes derived SQL/plan text into the LLM-adjacent skillsdi-agent-query-optimization/di-agent-flow-substrait-datastage, creating an indirect prompt-injection exposure path from that externally-authored code into the agent’s context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata