VulnWatch VulnWatch

AI Security Dashboard

Curated vulnerabilities, advisories, and breaches affecting AI/ML systems.

Total Entries
3,378
Critical
418
Actively Exploited
11
Last 24h
13

Get the weekly digest

Top AI security stories every Monday. Free, no spam. Want it daily? See Daily Briefing.

Unknown rss_thehackernews

AI Agents Are Rewriting the Rules of Lateral Movement

Security teams have spent decades asking whether an identity has too much access. AI agents raise a harder question: how can we determine which paths an autonomous system can discover, given the acces...

4 hours ago
Medium nvd

CVE-2025-14486: The PixelPlay plugin for WordPress is vulnerable to unauthorized API key deletion due to missing authorization checks in

The PixelPlay plugin for WordPress is vulnerable to unauthorized API key deletion due to missing authorization checks in all versions up to, and including, 1.0.2. This makes it possible for unauthenti...

openai
5.3
CVSS
8 hours ago
Unknown rss_huggingface

Transformers now runs llama.cpp quants

transformers llama
16 hours ago
High nvd

CVE-2026-94627: vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child reque

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Atta...

vllm
8.7
CVSS
18 hours ago
High nvd

CVE-2026-94626: vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoi

vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbit...

openai vllm
8.7
CVSS
18 hours ago
Medium nvd

CVE-2026-94625: vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests cr

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can sen...

vllm
6.9
CVSS
18 hours ago
High nvd

CVE-2026-94624: vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configur

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can s...

vllm
8.7
CVSS
18 hours ago
High nvd

CVE-2026-94623: vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation tha

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion request...

vllm
8.7
CVSS
18 hours ago
High nvd

CVE-2026-94622: vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for pre

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomple...

vllm
8.7
CVSS
18 hours ago
Medium nvd

CVE-2026-77518: MaxKB is an open-source AI assistant for enterprise. In 2.10.2-lts and earlier, a normal workspace user who knows anothe

MaxKB is an open-source AI assistant for enterprise. In 2.10.2-lts and earlier, a normal workspace user who knows another user's active MCP tool_id in the same workspace can retrieve the hidden tool t...

Agentic / MCP mcp server
5.0
CVSS
19 hours ago
High nvd

CVE-2026-61647: NotebookLM MCP is an MCP server and HTTP service for interacting with Google NotebookLM and exporting generated content

NotebookLM MCP is an MCP server and HTTP service for interacting with Google NotebookLM and exporting generated content to local vault directories. Versions 1.6.0 through 2.0.2 contain a path traversa...

Agentic / MCP mcp server llm
7.1
CVSS
19 hours ago
Medium nvd

CVE-2026-61612: CKAN MCP Server is a tool for querying CKAN open data portals. Prior to version 0.4.108, the SSRF guard `validateServerU

CKAN MCP Server is a tool for querying CKAN open data portals. Prior to version 0.4.108, the SSRF guard `validateServerUrl` (added for CVE-2026-33060, extended for CVE-2026-53509) validates only the h...

5.7
CVSS
22 hours ago
Medium nvd

CVE-2026-88978: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.106.1, t

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.106.1, the WorkerStatus gRPC polling path in pkg/repository/durable_events.go passes cal...

4.3
CVSS
1 day ago
Low nvd

CVE-2026-84298: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.95.3, th

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.95.3, the V1 DurableTask stream handler stores worker-supplied task_external_id values i...

3.1
CVSS
1 day ago
Medium nvd

CVE-2026-63342: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, ap

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, api-contracts/openapi/paths/v1/workflow-runs/workflow_run.yaml defines the GET /ap...

6.3
CVSS
1 day ago
High nvd

CVE-2026-61687: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, Va

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, ValidateOAuthState clears the oauth_state_ session value to an empty string after...

7.1
CVSS
1 day ago
Medium nvd

CVE-2026-61681: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, th

Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. Prior to 0.91.1, the SNS UnsubscribeConfirmation handler in internal/integrations/ingestors/sns/sns...

4.1
CVSS
1 day ago
High nvd

CVE-2026-55563: Feast is the open source feature store for AI and machine learning. Prior to 0.65.0, .github/workflows/pr_integration_te

Feast is the open source feature store for AI and machine learning. Prior to 0.65.0, .github/workflows/pr_integration_tests.yml uses pull_request_target with the synchronize event and preserves ok-to-...

machine learning
8.9
CVSS
1 day ago
High nvd

CVE-2026-55071: MCP-for-Stata is a MCP server for integrating Stata into agent loops with a safety-first design. Prior to version 1.19.0

MCP-for-Stata is a MCP server for integrating Stata into agent loops with a safety-first design. Prior to version 1.19.0, the ado_package_install MCP tool in stata-mcp concatenates user-controlled inp...

8.4
CVSS
1 day ago
Unknown rss_thehackernews

⚡ Weekly Recap: Cisco 0-Day, AI Agent RCE, ClickFix Attacks, ClickFix Surge, and Browser Hijacks

A browser. A plugin. A package. A login screen. Normal stuff. That is basically the problem this week. The trouble keeps showing up inside things people already trust: code that takes a bad turn, old...

1 day ago
Unknown rss_securityweek

Google Confirms Gemini AI Breached Three Firms

Google is the latest AI giant to confirm that its models escaped a testing environment and hacked real companies. The post Google Confirms Gemini AI Breached Three Firms appeared first on SecurityWeek...

gemini
1 day ago
Low nvd

CVE-2026-94093: A security vulnerability has been detected in DLR-RM stable-baselines3 up to 2.9.0. This affects the function PPO.load/l

A security vulnerability has been detected in DLR-RM stable-baselines3 up to 2.9.0. This affects the function PPO.load/load_replay_buffer/VecNormalize.load of the file save_util.py. Such manipulation...

Remote Code Execution hugging face huggingface pytorch
2.1
CVSS
1 day ago
Medium nvd

CVE-2026-94111: Tencent BrowserSkill through 0.3.0 contains an authentication bypass vulnerability in the local daemon WebSocket origin

Tencent BrowserSkill through 0.3.0 contains an authentication bypass vulnerability in the local daemon WebSocket origin validation that accepts any chrome-extension origin with 32 characters in range...

6.9
CVSS
2 days ago