dspy-ruby

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 includes agent tools that make arbitrary HTTP/GitHub API calls and search/fetch results (e.g., references to DSPy::Tools::GitHubCLIToolset.github_api_request, ApiToolset/SearchTool examples, and ReAct agents using external tools), so the agent is expected to read and interpret untrusted public third-party content (issues, PRs, web results), enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:25 PM