LLMHigh
CVE-2026-60086: PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection…
- Occurred
- Jul 10, 2026
- Published
- Jul 10, 2026
- Source
- NVD CVE
Summary
PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.
Tags
- CVE
- CVE-2026-60086
- cvss:MEDIUM
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Vulnerability allows prompt injection bypass in AI system, enabling malicious inputs to reach the model.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8