agent-platform-tuning
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow optionally ingests community datasets from Hugging Face (
load_dataset), which can contain arbitrary user-submitted text, but the agent must actively search or fetch them.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata