modelopt-release-cherry-pick
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The non-final-RC path runs
gh search prsagainst NVIDIA/Model-Optimizer and reads each merged PR's title, body, labels, and linked context, and anyone outside the org can open a PR that enters that feed without the agent selecting it first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata