CVE-2026-44223

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The extracthiddenstates speculative decoding proposer returns a tensor with an incorrect shape after the first decode step. This can be triggered by a remote attacker sending a request that uses sampling...

Agent against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these risks and for collecting training data to improve defenses. Existing state-of-the-art prompt injection red-teaming methods primarily rely on...

GHSA-MQ44-7P77-Q5H7 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, dask-kubernetes, dask-kubernetes-fips, apache-beam-python-3.13-sdk, airflow, lmcache-cuda-12.8, datahub-ingestion-fips, py3.13-scanner-test-libraries-aiohttp, awx, puppygraph-python, kserve-huggingfaceserver-cuda-13.3, kserve,...

CVE-2026-59881 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, dask-kubernetes, dask-kubernetes-fips, apache-beam-python-3.13-sdk, airflow, lmcache-cuda-12.8, datahub-ingestion-fips, py3.13-scanner-test-libraries-aiohttp, awx, puppygraph-python, kserve-huggingfaceserver-cuda-13.3, kserve,...

Malicious code in @or-sdk/knowledge-models (npm)

npm/@or-sdk/knowledge-models is affected by the large-scale, self-propagating npm supply-chain worm of 2026-08-04 the "Shai-Hulud: Here We Go Again" wave — the same campaign that began with the compromise of the keyv and cacheable maintainer account. The listed versions were trojanized and...

Open WebUI: /api/v1/channels/{id}/members exposes full user model including sensitive credentials

SummaryThe channel members endpoint serializes and returns full user models for channel participants, including settings objects. A normal user in a DM can retrieve admin-only sensitive configuration such as webhook URLs and tool server key material settings.ui.toolServers.key, which is not...

arkindex-base-worker (>=0.3.1b1, <=0.3.1rc2), labext-pkg (2.2.0) +3 more potentially affected by CVE-2026-61632 via pymdown-extensions (9.5.0)

pymdown-extensions PYPI version 9.5.0 is affected by a known vulnerability. The following packages have a transitive dependency on pymdown-extensions and may be impacted: - arkindex-base-worker =0.3.1b1, =0.0.4, =0.0.130, =2023.11.4 - stuffpages 0.7.4 Source cves: CVE-2026-61632 Source advisory:...

PYSEC-2026-3589 Open WebUI: Cross-user model-list exposure via static cache key in get_all_models (aiocache key= vs key_builder= misuse)

Summary The getallmodels handlers in routers/openai.py and routers/ollama.py intended to cache their permission-filtered model lists per user, but the @cached decorator was misconfigured: it passed a key= lambda instead of keybuilder=. In aiocache 0.12.3 the pinned version, key= is a static cache...

MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models

Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation process have been largely overlooked. We observe that each coordinate digit is...

The AI Act kicks into action, forces companies to be clear about AI chatbots

The European Union EU has started enforcing key parts of the AI Act, with immediate, visible consequences for chatbots, deepfakes and other consumer‑facing Artificial Intelligence AI systems. From August 2, what you'll likely notice are more "this is AI" labels, clearer rules for powerful...

More on the OpenAI Agent’s Attack on Hugging Face

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own...

CVE-2026-18607 Wavlink NU516 lighttpd upload.cgi strcpy stack-based overflow

A security vulnerability has been detected in Wavlink WN572, WN570H, WN573, WN529, WN530, WN531, WN535, etc. WN529, WN530, WN531, WN535, WN536, WN551, WN557 and NU516 up to 20260609. Affected by this issue is the function strcpy of the file upload.cgi of the component lighttpd. The manipulation o...

CVE-2026-18607

The CVE-2026-18607 affects Wavlink devices including WN572, WN570H, WN573, WN529, WN530, WN531, WN535, WN536, WN551, WN557, and NU516 (firmware up to 20260609). The vulnerability targets the strcpy function in lighttpd’s file upload.cgi, where manipulating the HTTP_COOKIE argument triggers a stac...

⚡ Weekly Recap: Rogue AI Models, $88M Bitcoin Theft, Water-System Attacks and Dangling DNS Hijacks

This week kept coming back to permission. A model crossed a boundary. A wallet trusted bad randomness. Webmail kept an intruder around. Public systems, package feeds, hotel networks, and login flows all gave away more than intended. Some of it was clever. Most of it was just access left lying...

EUVD-2026-52251

Sharp and Toshiba Tec MFPs multifunction printers for a certain market have been shipped with the user authentication feature disabled in the initial configuration. When used with the initial configuration, the address book editing and a range of features related to Document Filing can be accesse...

CVE-2026-18584

GL.iNet: Affects E5800/E750/X2000/X3000/XE3000/XE300 devices; eSIM LPA API v1, file /sdk/v1, improper authorization due to manipulation of a function. Attack possible only from local network; vendor confirmation exists. No patch/workaround details provided in the documents.

CVE-2026-20466

In sec boot, there is a possible escalation of privilege due to a heap buffer overflow. This could lead to local escalation of privilege, if an attacker has physical access to the device, with no additional execution privileges needed. User interaction is not needed for exploitation. Patch ID:...

Evading Chain-Of-Thought Monitoring through Model Poisoning

Chain-of-thought CoT monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoor...

PT-2026-67144

A vulnerability was detected in GL.iNet MT3000, MT6000, BE9300, BE3600, MT3600BE, E5800, BE6500, MT5000, X3000, XE3000 and MT2500 up to 20260707. The affected element is the function nas-web.get file list of the component APPS-NAS Module. Performing a manipulation results in heap-based buffer...

Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning

Incident response is currently managed by security operators using predefined playbooks, resulting in slow, labor-intensive security decision-making processes. Consequently, there is a growing need for automated incident response planning. Decision-theoretic approaches based on control,...