LLMHigh
CVE-2026-75062: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the defaul…
- Occurred
- Aug 26, 2026
- Published
- Aug 26, 2026
- Source
- NVD CVE
Summary
Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.
Tags
- CVE
- CVE-2026-75062
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: CVE describes eval injection vulnerability in LLM framework allowing arbitrary code execution via crafted prompts.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8