local-ai-models

Warn

Audited by Snyk on Jul 6, 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 free text is the user’s chat input passed at runtime into LanguageModelSession.streamResponse(to: text) / respond(to:), and that text is not authored by the operating user’s code (it comes from external users interacting with the app).

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 6, 2026, 08:53 AM
Issues
1
Security Audit — snyk — local-ai-models