AI/LLM CVE Reference
390 tracked vulnerabilities (90 critical, 195 high)
Vulnerabilities specifically affecting LLM frameworks, AI model serving, and adjacent ML infrastructure (LangChain, MLflow, Hugging Face, vLLM, llama.cpp) plus everything matching the keyword "prompt injection" or "large language model". Pulled from NVD, filtered to CVSS ≥ 4.0 and published within the last 5 years. Refreshed monthly.
Browse by topic
large language model114prompt injection110MLflow68LangChain57vLLM40Hugging Face27llama.cpp17
Recent (30 most recent)
- CVE-2026-44648HIGH · 7.52026-05-29 · large language model
- CVE-2026-44649CRITICAL · 9.82026-05-29 · large language model
- CVE-2026-44650CRITICAL · 9.12026-05-29 · large language model
- CVE-2026-45312CRITICAL · 9.92026-05-29 · prompt injection
- CVE-2026-46372HIGH · 8.52026-05-29 · large language model
- CVE-2026-4944HIGH · 8.82026-05-28 · vLLM
- CVE-2026-45134HIGH · 7.12026-05-27 · LangChain
- CVE-2026-44209HIGH · 7.52026-05-26 · prompt injection
- CVE-2026-44843HIGH · 8.22026-05-26 · LangChain
- CVE-2026-9540MEDIUM · 5.32026-05-26 · vLLM
- CVE-2026-2651CRITICAL · 92026-05-25 · MLflow
- CVE-2026-9353HIGH · 7.32026-05-24 · prompt injection
- CVE-2026-5817HIGH · 8.22026-05-22 · vLLM
- CVE-2026-2734MEDIUM · 6.52026-05-21 · MLflow
- CVE-2026-2611CRITICAL · 9.62026-05-19 · MLflow
- CVE-2026-4137HIGH · 72026-05-18 · MLflow
- CVE-2026-2652HIGH · 8.62026-05-15 · MLflow
- CVE-2026-45401HIGH · 8.52026-05-15 · LangChain
- CVE-2026-44827HIGH · 8.82026-05-14 · Hugging Face
- CVE-2026-42463HIGH · 8.12026-05-13 · large language model
- CVE-2026-44222MEDIUM · 6.52026-05-12 · prompt injection, large language model, vLLM
- CVE-2026-44223MEDIUM · 6.52026-05-12 · large language model, vLLM
- CVE-2026-44246HIGH · 7.22026-05-12 · prompt injection
- CVE-2026-2393HIGH · 7.12026-05-11 · MLflow
- CVE-2026-2614HIGH · 7.52026-05-11 · MLflow
- CVE-2026-31246MEDIUM · 6.52026-05-11 · prompt injection
- CVE-2026-43995CRITICAL · 9.82026-05-11 · large language model
- CVE-2026-41487MEDIUM · 5.42026-05-08 · large language model
- CVE-2026-42339HIGH · 7.12026-05-08 · large language model
- CVE-2026-33324HIGH · 8.82026-05-05 · prompt injection, large language model
Train your team on the AI vulnerability classes that matter.
Hands-on courses covering prompt injection, model security, and ML pipeline defense.
View AI Security Courses