CVE-2026-41432

CVE-2026-41432 affects New API versions prior to 0.12.10. The Stripe webhook endpoint is exposed at /api/stripe/webhook and is vulnerable when StripeWebhookSecret is empty, enabling an unauthenticated attacker to forge webhook events and fraudulently credit quota. Root causes listed across source...

CVE-2026-30886

The CVE-2026-30886 entry describes an Insecure Direct Object Reference (IDOR) in the video proxy endpoint GET /v1/videos/:task_id/content of the New API LLM gateway/AI asset manager. Before version 0.11.4-alpha.2, any authenticated user could access video content owned by others due to a missing ...

CVE-2026-42339

CVE-2026-42339 (New API: SSRF Filter Bypass via 0.0.0.0) Affects New API (LLM gateway) up to v0.11.9-alpha.1. The SSRF protection is incomplete: 0.0.0.0/8 is not checked, allowing a regular user with a valid API token to request multimodal endpoints (/v1/chat/completions, /v1/responses, /v1/messa...

CVE-2026-33655

The CVE-2026-33655 issue affects New API prior to version 0.12.0-alpha.1 where SSRF protection did not apply IP filtering to hostnames by default due to ApplyIPFilterForDomain being disabled. Authenticated users could configure notification URLs (Webhook, Bark, Gotify) that resolve to internal or...

CVE-2026-25591

Summary of CVE-2026-25591 (from connected advisory): A SQL LIKE wildcard injection in the authenticated endpoint /api/token/search allows crafted patterns to cause resource exhaustion and DoS by forcing expensive queries. The vulnerable code directly concatenates user-supplied keyword and token i...

CVE-2026-44342

CVE-2026-44342 describes a CSRF vulnerability in the New API where GET requests on state-changing endpoints GET /api/oauth/email/bind and GET /api/oauth/wechat/bind could allow an attacker to bind an email or OAuth identity for a logged-in user when session cookies are susceptible to cross-site n...

CVE-2026-25802

CVE context: The connected GHSA advisory GHSA-299V-8PQ9-5GJQ documents a potential XSS in a new API’s MarkdownRenderer component. The vulnerable path is in MarkdownRenderer.jsx (lines 212–231) that uses dangerouslySetInnerHTML to render model-generated HTML. Impact: potential XSS if the model out...