nemo-automodel-model-onboarding
Warn
Audited by Snyk on Jul 22, 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). SKILL.md instructs runtime retrieval of an outsider-authored Hugging Face
config.json(public web content) in Phase 1, which the agent will read and inject into its LLM context while classifying the architecture.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata