AI Threat AlertAI 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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 4307 resultsCVE-2026-113721virtualenv: symlink following allows file overwrite4.50.1%virtualenvOct 22HIGHCVE-2026-114510Flexible GraphRAG: Cypher injection via FalkorDB adapter7.10.4%flexible-graphragOct 22MEDICVE-2026-76297Splunk Enterprise: CSRF via GET disables federated search5.40.1%—Oct 21MEDICVE-2026-113716virtualenv: symlink following allows writes outside venv4.50.1%virtualenvOct 21MEDICVE-2026-113724virtualenv: symlink-following chmod alters file permissions4.50.2%virtualenvOct 21HIGHECVE-2026-113722virtualenv: shell injection in launcher path runs code7.80.3%virtualenvOct 21HIGHECVE-2026-114140nbconvert: path traversal allows arbitrary file write—0.5%jupyterOct 21MEDICVE-2026-114406Red Hat CA store: weak eMudhra intermediates enable TLS MITM6.80.3%rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Oct 21HIGHCVE-2026-114135Jupyter Server: kernel execute authz bypass via Gateway8.80.5%jupyterOct 21HIGHCVE-2026-112408SageMaker SDK: S3 bucket squatting enables RCE8.10.7%sagemakerOct 21LOWECVE-2026-113731djust: MCP tool path traversal enables local file probing3.30.2%—Oct 21UNKNCVE-2026-92206CrewAI: unsafe reflection in agent loader enables RCE—0.5%CrewAIOct 21HIGHCVE-2026-113725virtualenv: PS1 escaping flaw allows shell command execution7.80.3%virtualenvOct 21HIGHCVE-2026-114387Shopper: missing authorization allows admin escalation8.80.3%—Oct 21MEDICVE-2026-114386Pydantic AI Harness: tool-call limit bypass in CodeMode4.80.3%pydantic-ai-harnessOct 21MEDICVE-2026-92824libmodulemd: out-of-bounds read causes local DoS6.2—rhoai/odh-mlflow-operator-rhel9Oct 21MEDICVE-2026-92822libmodulemd: unbounded xmd recursion causes DoS6.2—rhoai/odh-mlflow-operator-rhel9Oct 21MEDICVE-2026-92823libmodulemd: decompression bomb causes local DoS6.2—rhoai/odh-mlflow-operator-rhel9Oct 21HIGHCVE-2026-114055vLLM: unvalidated mm_processor_kwargs enables remote DoS7.50.4%vllmOct 21MEDICVE-2026-114054vLLM: cache aliasing leaks cross-request media/KV state6.50.3%vllmOct 21Frequently 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