pdf-processor
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can enter the LLM context when the workflow fetches a user-supplied external PDF URL via Linkup (
/v1/proxy/orthogonal/runwithapi:"linkup", path:"/fetch", body:{url:...}) and then passes the extracted document content to ScrapeGraph/Riveter for AI extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata