dspy-ruby

Warn

Audited by Snyk on Mar 3, 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 agent/tool workflows that call external public services (e.g., references/toolsets.md and the module templates showing DSPy::Tools::ApiToolset and GitHubCLIToolset which perform arbitrary GET/POST and "github_api_request" calls) and ReAct agents are explicitly shown to consume those tool outputs to drive further actions, so untrusted third‑party content (public web/APIs, GitHub data) can influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:52 AM