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 1961 results — Active exploitationCVE-2025-55552PyTorch: integer overflow in rot90+randn_like causes DoS7.50.4%pytorchSep 25HIGHECVE-2025-55551PyTorch: DoS in linalg.lu via malformed slice op7.50.4%pytorchSep 25HIGHECVE-2025-9900libtiff: arbitrary write via crafted TIFF image8.81.0%rhaiis/vllm-cuda-rhel9Sep 23HIGHECVE-2025-6921Transformers: ReDoS in optimizer halts training pipelines7.50.5%transformersSep 23UNKNECVE-2025-59532OpenAI Codex CLI: sandbox escape via model-generated cwd—0.9%—Sep 22CRITECVE-2025-59528Flowise: Unauthenticated RCE via MCP config injection10.086.5%flowiseSep 22HIGHECVE-2025-59527Flowise: unauthenticated SSRF exposes internal network7.55.5%flowiseSep 22CRITECVE-2025-59434Flowise Cloud: cross-tenant env var exposure leaks API keys9.64.0%—Sep 22HIGHECVE-2025-9906Keras: safe_mode bypass enables RCE via model load7.30.2%kerasSep 19HIGHECVE-2025-9905Keras: safe_mode bypass enables RCE via .h5 model files7.30.2%kerasSep 19HIGHECVE-2025-10155picklescan: file extension bypass allows model RCE7.80.8%picklescanSep 17MEDIECVE-2025-6051Transformers: ReDoS in EnglishNormalizer exhausts CPU5.30.4%transformersSep 14CRITECVE-2025-58434Flowise: auth bypass in reset flow allows full ATO9.882.6%flowiseSep 12CRITECVE-2025-9556langchaingo: Jinja2 SSTI allows host filesystem read9.80.7%—Sep 12HIGHECVE-2025-6638HuggingFace Transformers: ReDoS in MarianTokenizer7.50.6%transformersSep 12HIGHECVE-2025-10156Picklescan: CRC bypass hides malicious pickle in ZIP7.51.5%picklescanSep 10HIGHECVE-2025-10157PickleScan: subclass bypass enables malicious model RCE8.30.8%picklescanSep 10HIGHECVE-2025-58757MONAI: unsafe pickle deserialization RCE in data pipeline8.80.6%monaiSep 9HIGHECVE-2025-58756MONAI: unsafe deserialization in CheckpointLoader allows RCE8.80.8%monaiSep 9HIGHECVE-2025-58755MONAI: path traversal allows arbitrary file write8.80.6%monaiSep 9Frequently 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