CVE-2026-47475

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service...

CVE-2026-47475

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service...

Vulnerabilities in Microsoft Azure

Microsoft has identified vulnerabilities in various Azure components. Malicious actors could exploit these vulnerabilities to cause denial-of-service attacks, circumvent security measures, or gain elevated privileges, potentially allowing them to access data that they were not originally authoriz...

Malicious code in openaiwrapper (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ea3d691208e7e5c443aa161241ca12c9b3eacb1b04428f886ea8c5fbec5a4d0c The package's postinstall lifecycle hook runs.init.js, which reads a hardcoded list of credential-shaped environment variables including NPMTOKEN,...

MAL-2026-10590 Malicious code in openaiwrapper (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ea3d691208e7e5c443aa161241ca12c9b3eacb1b04428f886ea8c5fbec5a4d0c The package's postinstall lifecycle hook runs.init.js, which reads a hardcoded list of credential-shaped environment variables including NPMTOKEN,...

CVE-2026-24271: Allocation of Resources Without Limits or Throttling

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service...

CVE-2026-47475: Reachable Assertion

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service...

PT-2026-58751

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service...

PT-2026-58757

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service...

CVE-2026-62186

OpenClaw versions before 2026.6.8 contain an authorization bypass vulnerability in OpenAI-compatible HTTP model overrides that allows lower-trust callers to perform actions requiring stronger authorization checks. Attackers can exploit misconfigured input paths to bypass admin authorization...

PYSEC-2026-3407 vllm has Improper Resource Shutdown or Release

A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used...

vllm has Improper Resource Shutdown or Release

A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used...

PYSEC-2026-2758 Open WebUI: Authenticated users can bypass model access control via exposed query parameter [AI-ASSISTED]

Summary An internal-only bypassfilter parameter is exposed on the /openai/chat/completions and /ollama/api/chat HTTP endpoints via FastAPI query string binding, allowing any authenticated user to append ?bypassfilter=true and bypass model access control checks to invoke admin-restricted models...

Open WebUI's responses passthrough endpoint lacks access control authorization

SummaryThe /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint generatechatcompletion checks model ownership, group membership, and...

PYSEC-2026-2557 Langchain-Chatchat Uses Insufficiently Random Values

A vulnerability was found in chatchat-space Langchain-Chatchat up to 0.3.1.3. The affected element is the function getfileid of the file libs/chatchat-server/chatchat/server/apiserver/openairoutes.py of the component Uploaded File Handler. Performing a manipulation results in insufficiently rando...

Langchain-Chatchat Uses Insufficiently Random Values

A vulnerability was found in chatchat-space Langchain-Chatchat up to 0.3.1.3. The affected element is the function getfileid of the file libs/chatchat-server/chatchat/server/apiserver/openairoutes.py of the component Uploaded File Handler. Performing a manipulation results in insufficiently rando...

PYSEC-2026-2559 Langchain-Chatchat has a Race Condition in its OpenAI-Compatible File Upload API

A vulnerability has been found in chatchat-space Langchain-Chatchat up to 0.3.1.3. Impacted is the function files of the file libs/chatchat-server/chatchat/server/apiserver/openairoutes.py of the component OpenAI-Compatible File Upload API. Such manipulation of the argument file.filename leads to...

PYSEC-2026-2329 AgentScope vulnerable to Server-Side Request Forgery

A vulnerability was identified in modelscope agentscope up to 1.0.18. Affected by this issue is the function parseurl/prepareimage/openaiaudiototext of the file src/agentscope/tool/multimodality/openaitools.py of the component Cloud Metadata Endpoint. Such manipulation of the argument...

PraisonAI: Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without Rate Limits

SummaryThe /media-stream WebSocket endpoint in PraisonAI's call module accepts connections from any client without authentication or Twilio signature validation. Each connection opens an authenticated session to OpenAI's Realtime API using the server's API key. There are no limits on concurrent...

PYSEC-2026-2920 PraisonAI: Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without Rate Limits

Summary The /media-stream WebSocket endpoint in PraisonAI's call module accepts connections from any client without authentication or Twilio signature validation. Each connection opens an authenticated session to OpenAI's Realtime API using the server's API key. There are no limits on concurrent...