LLMHigh
CVE-2026-61439: PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block…
- Occurred
- Jul 11, 2026
- Published
- Jul 11, 2026
- Source
- NVD CVE
Summary
PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.
Tags
- CVE
- CVE-2026-61439
- cvss:HIGH
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Prompt injection vulnerability in LLM system allows unauthorized tool invocations and data extraction.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8