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 169 results — Critical severity, has patchCVE-2026-116692MLflow: scorer deserialization allows unauthenticated RCE9.80.7%mlflowOct 27CRITCVE-2026-48705MONAI: NaN/inf DICOM input causes DoS and corrupt inference9.3—monaiOct 27CRITCVE-2026-114612LiteLLM: forged admin token enables RCE via MCP stdio9.90.3%litellmOct 22CRITECVE-2026-112403Pillow: heap overflow via lossless JPEG in thumbnail()—0.9%PillowOct 20CRITCVE-2026-111058Mercury: missing auth allows anonymous kernel RCE9.80.5%mercuryOct 19CRITECVE-2026-111057Mercury: regex blocklist bypass allows unauthenticated RCE10.00.7%mercuryOct 19CRITCVE-2026-94603Podman: checkpoint images override sandbox on run10.00.5%github.com/containers/podmanOct 15CRITECVE-2026-62176PraisonAI: code injection in deploy API enables RCE9.10.5%PraisonAIOct 7CRITECVE-2026-105697Langflow: MCP stdio command injection allows host RCE9.90.9%lfxOct 5CRITECVE-2026-92938vm2: node:sqlite sandbox escape allows native code RCE9.90.6%vm2Oct 1CRITECVE-2026-92939vm2: native code exec via crypto.setEngine sandbox escape9.90.6%vm2Oct 1CRITECVE-2026-61732Decepticon: ChatML token injection yields sandbox RCE10.01.5%decepticon-sdkSep 24CRITCVE-2026-77244MCP Atlassian: unauthenticated access to operator Jira/Confluence10.00.3%mcp-atlassianSep 22CRITCVE-2025-66455LMDeploy: pickle deserialization RCE in DistServe9.81.3%lmdeploySep 18CRITECVE-2025-59953LMDeploy: unsafe pickle deserialization allows RCE9.80.9%lmdeploySep 16CRITECVE-2026-79657NLTK: pickle allowlist bypass enables RCE9.81.3%nltkSep 8CRITECVE-2026-71428unstructured: SSRF via url= param exposes internal APIs9.30.4%unstructuredSep 3CRITECVE-2026-55634Pimcore: DataObject field-name injection → RCE9.90.7%pimcore/pimcoreAug 28CRITECVE-2026-55220Pimcore: PHP deserialization flaw enables RCE—0.7%pimcore/pimcoreAug 28CRITECVE-2026-37004LiteLLM: unauth SSTI in /prompts/test enables RCE9.80.8%litellmAug 27Frequently 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