LLMHigh
CVE-2026-33833: Improper neutralization of special elements in output used by a downstream component ('injection') i…
- Occurred
- May 12, 2026
- Published
- May 12, 2026
- Source
- NVD CVE
Summary
Improper neutralization of special elements in output used by a downstream component ('injection') in Azure Machine Learning allows an unauthorized attacker to perform spoofing over a network.
Tags
- CVE
- CVE-2026-33833
- cvss:HIGH
Classification
Category confidence: 85%
Severity confidence: 90%
Rationale: CVE describes injection vulnerability in Azure ML allowing spoofing, which is a security flaw in AI system.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8