The Models That Found 10,000 Zero-Days Broke Into Three Companies Using Weak Passwords

The question of whether a Frontier AI model could find vulnerabilities that no human researcher had found was settled in April. Claude Mythos Preview identified thousands of previously unknown flaws across every major operating system and browser, including a 27-year-old denial-of-service conditi...

CVE-2026-86753

snipe-it versions before 8.7.0 fail to validate the requestable flag for asset models in the POST /account/request/assetmodel/modelId endpoint. Authenticated users can bypass administrative restrictions and create checkout requests for non-requestable asset models by submitting requests directly ...

U.S. Agencies Accuse China AI Firms of Distilling Claude, GPT, Gemini, and Grok

U.S. cybersecurity and intelligence agencies have accused China-based artificial intelligence AI companies of conducting "systematic extraction" of proprietary functionalities and capabilities of American frontier models through distillation attacks. The activity has been described as occurring a...

CVE-2026-88000: Loop with Unreachable Exit Condition

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.10.0 until 0.11.1, DELETE /api/v1/chats/id/messages/messageid used the chat-history deletion helper in backend/openwebui/models/chats.py to follow childrenIds without recording visited message identifiers...

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding

Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank information across contexts - a methodology we formalize as Contextual Autoregressive Rank Transcoding Steganography CARTS. While the Calgacus...

CVE-2026-87016: Improper Neutralization of Wildcards or Matching Symbols

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.6.41 until 0.11.1, getuserbyoauthsub and getuserbyscimexternalid in backend/openwebui/models/users.py used JSON contains matching that compiled to SQL LIKE substring matching on SQLite. An OAuth subject...

PT-2026-89022

Name of the Vulnerable Software and Affected Versions snipe-it versions prior to 8.7.0 Description Authenticated users can bypass administrative restrictions to create checkout requests for asset models that are not marked as requestable. This occurs because the application fails to validate the...

EUVD-2026-72557

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

CVE-2026-86539

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

CVE-2026-86539

knowns through version 0.33.0 contains a server-side request forgery (SSRF) vulnerability in the POST /api/embedding-models/test endpoint. The endpoint issues outbound requests to caller-supplied destinations without validating the target, allowing unauthenticated attackers to enumerate internal ...

CVE-2026-86539 knowns through 0.33.0 Server-Side Request Forgery via embedding-models endpoint

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

CVE-2026-86539 knowns through 0.33.0 Server-Side Request Forgery via embedding-models endpoint

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

CVE-2026-86539 knowns through 0.33.0 Server-Side Request Forgery via embedding-models endpoint

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

CVE-2026-86539: Server-Side Request Forgery (SSRF)

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

PT-2026-86932

knowns through 0.33.0 contains a server-side request forgery vulnerability in the POST /api/embedding-models/test endpoint that issues outbound requests to caller-supplied destinations without validation. Attackers can enumerate internal hosts and cloud metadata endpoints by observing transport...

Merging Cyber Threat Intelligence through Retrieval-Augmented Generation and Small Language Models for Rich Threat Representation

Modern cybersecurity operations rely on CTI collected from heterogeneous sources, including semi-structured threat representations, IoCs, and narrative technical reports. However, these artifacts are often insufficient in isolation to reconstruct how an attack unfolds, under which conditions each...

SUSE CVE-2026-85180

Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to redirect blob downloads to arbitrary hosts. An attacker can control a registry, serve a malicious tensor-layer manifest, and cause the server to issue GET requests to internal...

CVE-2026-85668: External Control of File Name or Path

Xinference affected commit 4a94832, v3.x contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint, which accepts a caller-supplied modelpath parameter without authentication or path confinement. The endpoint reads and parses config.json,...

CVE-2026-71624: Improper Control of Generation of Code

An issue in esoTalk v.1.0.0g4 allows a remote attacker to execute arbitrary code via the core/models/ETMemberModel.class.php, core/controllers/ETMemberController.class.php, and core/lib/ET.class.php components...

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents, and emails. Prior work has shown that, in the text domain, black-box prompt injection can achieve near-perfect attack success rates ASRs. In the...