research-workflow
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 workflow explicitly requires "Web Search Research" (blog posts, community knowledge) and "GitHub Repository Research," which instructs the agent to fetch and read untrusted public/user-generated content from the open web and public repositories as part of its analysis.
Audit Metadata