AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

79

New This Week

16

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1092 results — no patch
MEDIUM

mistune: math plugin XSS bypasses escape=True control

CVE-2026-44708
6.1
Code Execution Data Extraction Auth Bypass Plugin Framework
mistune CWE-79 463 4 ATLAS
CRITICAL

cline: WebSocket auth bypass enables terminal RCE

CVE-2026-44211
9.6
Auth Bypass Code Execution Data Leakage Agent Plugin
CWE-306 7 ATLAS
MEDIUM

n8n-MCP: credential logging exposes OAuth tokens in HTTP mode

CVE-2026-42282
4.3
Data Leakage Data Extraction Agent Plugin
CWE-532 4 ATLAS
HIGH

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to...

CVE-2026-42271
8.8
EPSS 0.0%
litellm CWE-77 4
CRITICAL

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used...

CVE-2026-42208
9.8
EPSS 0.1%
litellm CWE-89 4
UNKNOWN

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test...

CVE-2026-42203
--
EPSS 0.0%
CWE-1336
CRITICAL

Compromise of PyTorch Lightning PyPi Package Versions

CVE-2026-44484
--
pytorch-lightning CWE-506 1.6K
MEDIUM

Vercel: Non-interactive mode includes CLI arguments in suggested command output

CVE-2026-44479
5.5
CWE-200
LOW

ciguard: discover_pipeline_files follows symlinks out of scan root

CVE-2026-44220
--
CWE-59
MEDIUM

wireshark-mcp vulnerable to arbitrary file write via export_objects when WIRESHARK_MCP_ALLOWED_DIRS is not configured

CVE-2026-43901
6.8
CWE-22
HIGH

PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

CVE-2026-42079
8.6
EPSS 0.0%
CWE-95
MEDIUM

LobeHub has a Cross-Site Scripting issue that escalates to Remote Code Execution

CVE-2026-42045
6.2
@lobehub/lobehub CWE-78 3.5K
LOW

A vulnerability was found in chatchat-space Langchain-Chatchat up to 0.3.1.3. The affected element is the function _get_file_id of the file...

CVE-2026-7847
2.6
EPSS 0.0%
langchain-chatchat CWE-310 2.6K
LOW

A vulnerability has been found in chatchat-space Langchain-Chatchat up to 0.3.1.3. Impacted is the function files of the file...

CVE-2026-7846
2.6
EPSS 0.0%
langchain-chatchat CWE-362 2.6K
LOW

A flaw has been found in chatchat-space Langchain-Chatchat up to 0.3.1.3. This issue affects the function PIL.Image.tobytes of the file...

CVE-2026-7845
2.6
EPSS 0.0%
langchain-chatchat CWE-327 2.6K
MEDIUM

A vulnerability was detected in chatchat-space Langchain-Chatchat up to 0.3.1.3. This vulnerability affects the function...

CVE-2026-7844
6.3
EPSS 0.0%
CWE-287
CRITICAL

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file...

CVE-2026-7482
9.1
EPSS 0.1%
MEDIUM

A weakness has been identified in langflow-ai langflow up to 1.8.4. This affects the function eval of the file...

CVE-2026-7700
6.3
EPSS 0.0%
CWE-74
MEDIUM

A vulnerability was determined in langflow-ai langflow up to 1.8.4. Affected by this issue is the function CodeParser.parse_callable_details of the file...

CVE-2026-7687
6.3
EPSS 1.1%
CWE-74
MEDIUM

A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function get_tokenizer of the file...

CVE-2026-7669
5.6
EPSS 0.1%
sglang CWE-20 7.8K

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial