Newly released CVEs across every platform — sleek to read, verbose on demand, and served raw as markdown for AI and agent ingestion. Severity reads as depth: the deeper the contact, the graver the threat.
Depth = severity + exploitation
CVE-2026-47214High· 7.1Docling simplifies document processing by parsing diverse formats and providing integrations with the generative AI ecosystem. Prior to 2.94.0, the HTML backend has unsafe URI and path handling. This vulnerability is fixed in 2.94.0.
CVE-2026-44020High· 7.5Docling: Unsafe XML Entity Expansion in USPTO Patent Backend
CVE-2026-44018Medium· 5.5Docling: Unsafe Archive Extraction and XML Parsing in METS-GBS Backend
CVE-2026-44016High· 8.2Docling: Unsafe Playwright-based HTML Rendering
CVE-2026-44017High· 7.5Docling: Unsafe Zip Extraction in EasyOCR Model Download
CVE-2026-44022Medium· 5.5Docling: Potential Path Traversal via LaTeX \includegraphics and \input Commands
CVE-2026-31247High· 7.5Docling's JATS XML backend is vulnerable to XML Entity Expansion (XXE) attacks
CVE-2026-31248High· 7.5Docling's METS GBS backend is vulnerable to XML Entity Expansion (XXE) attacks
A summary of everything that shipped over the last two weeks — the whole corpus is open, agents get change feeds, alias resolution and EPSS movers, and the data now includes CVE.org, vendor CSAF, aggregated exploits and per-source scores.
A step-by-step guide to plugging VulnSea into automated and agentic workflows — poll the delta, triage without burning tokens, match an SBOM, and let an MCP-native model do the reasoning.
CVE and 0day intelligence that reads like an instrument — built for analysts and AI agents alike. Here's what it does and where it's going.