AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,019

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 3019 results
MEDIUM

Coder: X-Forwarded-Host spoof leaks victim app data

CVE-2026-55430
5.8
EPSS 0.1%
Auth Bypass Privacy Violation Agent API
github.com/coder/coder/v2 Patch: 2.34.2 CWE-345 6.2K 2 ATLAS
HIGH

Coder: agent IP spoofing hijacks workspace traffic

CVE-2026-55428
8.2
EPSS 0.2%
Auth Bypass Privacy Violation Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-285 6.2K
HIGH

Coder: cross-workspace agent hijack via app ID reuse

CVE-2026-55429
8.7
EPSS 0.3%
Auth Bypass Privacy Violation Agent API
github.com/coder/coder/v2 Patch: 2.34.2 CWE-639 6.2K 1 ATLAS
MEDIUM

Coder: unbounded FileSize crashes coderd via OOM

CVE-2026-55079
4.9
EPSS 0.3%
DoS Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-789 6.2K
HIGH

Coder: SSH config injection via config-ssh enables RCE

CVE-2026-55427
8.3
EPSS 0.3%
Code Execution Supply Chain Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-74 6.2K 2 ATLAS
HIGH

Coder: user-admin can hijack owner accounts

CVE-2026-55077
7.2
EPSS 0.3%
Auth Bypass Code Execution Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-285 6.2K 2 ATLAS
HIGH

Coder: OIDC auth bypass enables account takeover

CVE-2026-55075
7.4
EPSS 0.3%
Auth Bypass Privacy Violation Agent Training Data
github.com/coder/coder/v2 Patch: 2.34.2 CWE-287 6.2K 3 ATLAS
HIGH

Coder: OIDC type-confusion enables account takeover

CVE-2026-55076
7.4
EPSS 0.3%
Auth Bypass Agent API
github.com/coder/coder/v2 Patch: 2.34.2 CWE-287 6.2K 3 ATLAS
HIGH EXPLOIT AVAIL

Langroid: auth bypass invokes disabled tools via raw JSON

CVE-2026-54771
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
langroid Patch: 0.65.3 CWE-74 4 3 ATLAS
CRITICAL EXPLOIT AVAIL

Langroid: prompt injection to RCE via broken eval() sandbox

CVE-2026-54769
10.0
EPSS 0.6%
Prompt Injection Code Execution Agent Framework
langroid Patch: 0.65.2 CWE-94 4 6 ATLAS
UNKNOWN EXPLOIT AVAIL

Langroid: SQLChatAgent regex bypass exposes pg_read_file

CVE-2026-54760
--
EPSS 0.6%
Auth Bypass Data Extraction Prompt Injection Agent Framework
langroid Patch: 0.65.1 CWE-22 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: audio upload OOMs process before size check

CVE-2026-55646
6.5
EPSS 0.3%
DoS Inference API
vllm Patch: 0.24.0 CWE-400 130 2 ATLAS
MEDIUM

OpenAI Codex: prompt injection exfils data via images

CVE-2026-14898
6.5
EPSS 0.3%
Prompt Injection Data Leakage Agent API
4 ATLAS
MEDIUM

OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap

CVE-2026-40257
5.5
EPSS 0.1%
DoS Code Execution Inference Model
CWE-787 1 ATLAS
MEDIUM

LangSmith SDK: arbitrary file read via TracingMiddleware

CVE-2026-59152
5.0
EPSS 0.2%
Data Leakage Auth Bypass Framework Agent
langsmith-sdk 3.0K 3 ATLAS
LOW EXPLOIT AVAIL

LangGraph: weak hash in task cache risks poisoning

CVE-2026-14742
3.1
EPSS 0.2%
Data Leakage Framework Agent
langgraph CWE-327 3.7K 2 ATLAS
LOW EXPLOIT AVAIL

exo: weak hash algorithm in vision feature cache key

CVE-2026-14738
3.7
EPSS 0.2%
Data Leakage Privacy Violation Inference Framework
1 ATLAS
MEDIUM EXPLOIT AVAIL

ONNX: OOB read in shape inference parsing untrusted models

CVE-2026-14647
4.3
EPSS 0.3%
Code Execution DoS Model Framework
onnx CWE-119 1.1K 2 ATLAS
CRITICAL EXPLOIT AVAIL

fickling: shared-state bug disables ML pickle allowlist check

CVE-2026-14535
9.8
EPSS 0.3%
Supply Chain Code Execution Model Training Data
fickling 61 3 ATLAS
HIGH EXPLOIT AVAIL

fickling: denylist gaps let malicious pickles execute

CVE-2026-14534
8.8
EPSS 0.4%
Code Execution Supply Chain Framework Model
fickling 61 5 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

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