dspy-prompting
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's examples include a ReAct search_tool labeled "Search Wikipedia" and a MultiHopQA that calls dspy.Retrieve and then concatenates retrieved "passages" for the model to read, which clearly ingests public third‑party content (Wikipedia/public web) into the agent's workflow.
Audit Metadata