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

3,021

AI/ML CVEs Tracked

424

Critical

113

New This Week

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 1076 results — has patch

Severity CVE ID Summary CVSS EPSS Package Date

HIGH GHSA-mgq6-vr84-7m2j OpenClaw: QQBot approval button auth bypass 8.0 — openclaw Jul 2 HIGH GHSA-rggc-m335-3wvj OpenClaw: forged identity headers bypass proxy auth — — openclaw Jul 2 HIGH GHSA-2j8v-hwgc-x698 OpenClaw: TOCTOU in shell wrapper bypasses command allowlist — — Openclaw Jul 2 MEDI GHSA-qh2f-99mv-mrcf OpenClaw: exec denylist bypass in bundled MCP loopback — — openclaw Jul 2 HIGH GHSA-xww8-gqvh-92x9 OpenClaw: truncated approval UI masks exec payload 8.0 — openclaw Jul 2 CRIT CVE-2026-50027 mcp-memory-service: auth bypass on document API 9.8 — mcp-memory-service Jul 2 MEDI GHSA-9c3v-684m-579c OpenClaw: MCP SSE redirect leaks Authorization headers 6.5 — openclaw Jul 1 HIGH CVE-2026-49857 auth-fetch-mcp: SSRF bypass via IPv6 loopback 7.4 — auth-fetch-mcp Jul 1 HIGH E CVE-2026-57516 Ray: RCE via pickle/torch deserialization in WebDataset 8.8 0.6% ray Jul 1 MEDI E CVE-2026-12480 Keras: incomplete fix reopens HDF5 arbitrary file read 5.5 0.1% keras Jul 1 HIGH CVE-2026-55607 Claude Code: worktree bug enables sandbox-escape RCE — 0.6% @anthropic-ai/claude-code Jun 29 MEDI GHSA-j7f5-gfqm-pcx3 Pterodactyl panel: email endpoint leaks user enumeration — — pterodactyl/panel Jun 26 CRIT E CVE-2026-54158 SiYuan: XSS→RCE via workspace sync in Electron app 9.9 0.3% github.com/siyuan-note/siyuan/kernel Jun 24 LOW CVE-2026-55542 Snipe-IT: auth bypass exposes S3 signature image URLs — 0.2% snipe/snipe-it Jun 23 MEDI E CVE-2026-52816 Gogs: XSS via data URI in ipynb sanitizer endpoint — 0.5% gogs.io/gogs Jun 23 HIGH E CVE-2026-52812 Gogs LFS: cross-tenant object disclosure via dedupe bypass — 0.2% gogs.io/gogs Jun 23 HIGH E CVE-2026-52798 Gogs: Stored XSS via .ipynb Markdown re-render bypass 8.9 0.3% gogs.io/gogs Jun 22 HIGH E CVE-2026-54353 Budibase: SSRF via DNS rebinding in automation steps 8.5 0.2% @budibase/backend-core Jun 22 CRIT E CVE-2026-54352 Budibase: zip symlink bypass exposes all server secrets 9.6 0.4% @budibase/server Jun 22 MEDI CVE-2026-48500 Filament: unauth file upload drains disk/inflates costs 6.5 0.3% filament/filament Jun 22

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