dspy-ruby

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill includes examples that ingest untrusted external content for the agent to read and act on—e.g., DSPy::Image.from_url("https://example.com/image.jpg") in the multimodal docs (references/core-concepts.md) and WebSearchTool/ResearchAgent and ReAct agent examples in assets/module-template.rb that perform web searches and return arbitrary results for the agent to interpret—so it clearly consumes public, user-generated third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:12 PM