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 37 of 48
Current
SeverityCVECVSS
CRITICALCVE-2025-664559.8
HIGHGHSA-39wr-7q6h-cf687.5
MEDIUMCVE-2026-938405.3
MEDIUMCVE-2026-939894.3
CRITICALCVE-2026-46649-
MEDIUMCVE-2026-551796.5
MEDIUMCVE-2026-598164.3
HIGHCVE-2026-61647-
HIGHCVE-2026-946267.5
HIGHCVE-2026-946237.5
HIGHCVE-2026-946277.5
HIGHCVE-2026-552107.4
MEDIUMCVE-2025-144865.3
MEDIUMCVE-2026-616125.7
CRITICALCVE-2026-941279.8
MEDIUMCVE-2026-857095.3
HIGHCVE-2026-77274-
CRITICALCVE-2026-7724410.0
MEDIUMCVE-2026-772655.9
HIGHCVE-2026-772427.5

Page 37 of 48