AI/LLM CVE Reference
436 tracked vulnerabilities (100 critical, 218 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 model139prompt injection122MLflow71LangChain58vLLM52Hugging Face29llama.cpp17
Recent (30 most recent)
- CVE-2026-10564HIGH · 8.22026-06-30 · prompt injection
- CVE-2026-58116CRITICAL · 9.82026-06-30 · Hugging Face
- CVE-2026-55607HIGH · 8.82026-06-29 · prompt injection
- CVE-2026-13484MEDIUM · 52026-06-28 · MLflow
- CVE-2026-48719HIGH · 82026-06-24 · prompt injection
- CVE-2025-66389HIGH · 7.52026-06-22 · prompt injection
- CVE-2026-41523HIGH · 7.52026-06-22 · large language model, vLLM
- CVE-2026-47155MEDIUM · 6.52026-06-22 · large language model, vLLM
- CVE-2026-48746CRITICAL · 9.12026-06-22 · large language model, vLLM
- CVE-2026-53923HIGH · 7.52026-06-22 · large language model, vLLM
- CVE-2026-54232HIGH · 8.82026-06-22 · large language model, vLLM
- CVE-2026-54233MEDIUM · 6.52026-06-22 · large language model, vLLM
- CVE-2026-54235MEDIUM · 6.52026-06-22 · large language model, vLLM
- CVE-2026-54236MEDIUM · 5.32026-06-22 · large language model, vLLM
- CVE-2026-55443MEDIUM · 5.12026-06-22 · LangChain
- CVE-2024-58351CRITICAL · 9.82026-06-20 · prompt injection
- CVE-2025-71379MEDIUM · 4.32026-06-20 · vLLM
- CVE-2026-56340HIGH · 8.82026-06-20 · vLLM
- CVE-2026-12045CRITICAL · 92026-06-19 · prompt injection
- CVE-2026-22551MEDIUM · 6.52026-06-18 · prompt injection
- CVE-2026-44688HIGH · 8.82026-06-18 · prompt injection
- CVE-2026-46580HIGH · 8.82026-06-18 · prompt injection
- CVE-2026-12491MEDIUM · 4.82026-06-17 · large language model, vLLM
- CVE-2026-55743CRITICAL · 9.62026-06-17 · prompt injection
- CVE-2026-42853MEDIUM · 6.52026-06-12 · prompt injection
- CVE-2026-5497HIGH · 7.52026-06-11 · vLLM
- CVE-2026-46432HIGH · 7.82026-06-10 · large language model
- CVE-2026-46517HIGH · 7.82026-06-10 · large language model
- CVE-2026-42861CRITICAL · 9.62026-06-08 · large language model
- CVE-2026-42862MEDIUM · 52026-06-08 · 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