vote-predict
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The runtime path ingests outsider-authored free text via
sampler.sample_personas(..., source="nemotron_usa", mode="stream"), where the LLM-readable persona content is sourced from an external/public dataset (“nemotron_usa”) rather than authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata