foundation-models
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). Outsider free text can enter the LLM context via the runtime user prompt passed to
session.respond(to:)/streamResponse(to:)(the operating user did not choose the content of that text beyond providing it as input), which the framework then includes in the model’s transcript/context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata