AI Component

API

AI APIs are the boundary between the application and the model. Self-hosted inference servers (vLLM, Triton, Ollama, TGI) and third-party gateways (LiteLLM, OpenRouter) expose OpenAI-compatible endpoints, and the same web-app vulnerability classes appear here: missing or weak authentication on /v1/chat/completions, broken authorization between tenants, lack of rate limiting that lets an attacker drain quota or burn GPU time, and overly permissive CORS that leaks API keys from browser-side calls. The blast radius is unusual: a single auth-bypass on an inference endpoint exposes both data and compute, and in the case of paid hosted models, directly costs money. We have seen production CVEs across most popular self-hosted servers in the last 18 months. Defenses: require auth on every endpoint, per-tenant rate limits, separate key scopes for read vs admin, and pin server versions aggressively.

948
Total CVEs
48
Pages
Page 3 of 48
Current
SeverityCVECVSS
MEDIUMCVE-2024-136986.5
MEDIUMCVE-2025-297706.5
UNKNOWNCVE-2024-11037-
UNKNOWNCVE-2024-12775-
HIGHCVE-2024-79597.7
MEDIUMCVE-2025-318434.3
HIGHCVE-2025-50187.1
MEDIUMCVE-2025-70216.5
MEDIUMCVE-2025-67166.4
MEDIUMCVE-2025-536216.9
MEDIUMCVE-2025-77806.5
HIGHCVE-2025-77257.2
CRITICALCVE-2025-5376710.0
CRITICALCVE-2025-594349.6
MEDIUMCVE-2025-605114.3
MEDIUMCVE-2025-123604.3
MEDIUMCVE-2025-119724.9
MEDIUMCVE-2025-127324.3
HIGHCVE-2025-129737.2
MEDIUMCVE-2025-133544.3

Page 3 of 48