NYC

dspy-framework

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt includes multiple examples that pass API keys directly (e.g., api_key='YOUR_API_KEY', os.environ["LANGCHAIN_API_KEY"] = "your-key") which instructs embedding secrets verbatim in code/config, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill demonstrates runtime ingestion of untrusted third-party content via retrieval and web tools — e.g., dspy.Retrieve used in RAG pipelines (retriever(question).passages) and the ReAct example that includes a web_search tool — and the agent is expected to read and use those passages as context.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:42 PM