cold-start-interview
Warn
Audited by Snyk on Jul 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: 0.75). Outsider free text can enter the LLM context when the runtime “seed documents” step ingests user-provided signed agreements/templates (file paths, Drive links, CLM record IDs) and extracts their body text, which is not authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata