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 34 of 48
Current
SeverityCVECVSS
HIGHCVE-2026-856667.5
HIGHCVE-2026-856737.5
HIGHCVE-2026-856867.5
HIGHCVE-2026-727948.6
MEDIUMCVE-2026-863326.5
MEDIUMCVE-2026-86073-
HIGHCVE-2026-86082-
HIGHCVE-2026-86075-
MEDIUMCVE-2026-878205.3
HIGHCVE-2026-591587.5
MEDIUMCVE-2026-870134.3
HIGHCVE-2026-870117.5
MEDIUMCVE-2026-870156.8
HIGHCVE-2026-870168.1
MEDIUMCVE-2026-879974.3
HIGHCVE-2026-879987.1
MEDIUMCVE-2026-880056.5
HIGHCVE-2026-88009-
HIGHGHSA-m3wp-48jr-vr4g7.5
HIGHGHSA-wfgq-w7cq-qj7j7.2

Page 34 of 48