ai-content-pipeline
Warn
Audited by Snyk on May 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The workflow’s “Research -> Content” pattern uses
tavily/search-assistant, which at runtime fetches public web pages/snippets and feeds that retrieved free text into the downstream LLM context for summarization/content generation (public web content = outsider-authored text).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata