ZeroHour
Organization

Censys

1 mentions in 7 days · 2 in 30 days · 2 total · first seen · last

Timeline

The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet

Researchers counted 36,769 publicly reachable self-hosted AI endpoints, only about 2% behind HTTP authentication, exposing Ollama, vLLM, and Flowise to abuse.

A Mysterium VPN study found 36,769 self-hosted AI endpoints reachable through internet scanning, with only 2.02% returning an HTTP authentication challenge. Open WebUI accounted for 18,529 reachable instances, Ollama for 6,935 fingerprinted hosts, and 5,223 agent-builder and workflow platforms were exposed, often holding API keys, database credentials, and other secrets. The report highlights LLMjacking risk from exposed Ollama APIs, a critical Flowise bug (CVE-2026-40933), leaked n8n tokens, and prior SentinelOne/Censys research finding roughly 175,000 exposed Ollama hosts in 130 countries.

⚡ Weekly Recap: AI-Powered PLC Attacks, GitLab Attacks, Stripe Key Leaks and More

US agencies warn of AI-assisted attacks on exposed Siemens PLCs; the week also saw GitLab CVE-2026-19478 exploited and trojanized npm packages found.

The weekly recap leads with a US government warning that threat actors use AI-generated scripts and Censys/ZoomEye scanning to attack internet-exposed Siemens S7 PLCs in water, energy and manufacturing, calling it an active threat. Other stories include active exploitation of GitLab CVE-2026-19478 (CVSS 9.4, unauthenticated project rewriting), 14 trojanized npm packages delivering the RedC2 4.0 Linux backdoor, and the Zombie Card attack that revives expired Visa cards for contactless payment fraud. It also covers suspected Russian clusters UNC6293, UNC7005 and UNC5976 phishing campaigns, a faster Cloudflare Workers Spectre JWT leak, and a bespoke Cl0p JSP web shell deployed after exploiting PTC Windchill flaws.

The Hacker News · 18d agoThreat actor in the wildCVE-2026-194781

Related CVEs

  • Flowise is a drag & drop user interface to build a customized large language model flow.
    Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, due to unsafe serialization of stdio commands in the MCP adapter, an authenticated attacker can add an MCP stdio server with an arbitrary command, achieving command execution. The vulnerability lies in a bug in the input sanitization from the “Custom MCP” configuration in http://localhost:3000/canvas - where any user can add a new MCP, when doing so - adding a new MCP using stdio, the user can add any command, even though your code have input sanitization checks such as…
    · flowiseai flowise PoC
  • Unauthenticated GraphQL Code Injection in GitLab CE/EE Enables Data Tampering
    GitLab has patched a critical (CVSS 9.1) code injection flaw (CWE-94) in how GitLab Community Edition (CE) and Enterprise Edition (EE) process GraphQL directives. Under certain conditions, an unauthenticated remote attacker can abuse a GraphQL directive to modify or delete public projects and user data on affected instances, requiring no privileges or user interaction; the impact is to integrity and availability, not confidentiality. Affected versions span all GitLab CE/EE releases from 18.2 before 18.11.11, 19.0 before 19.0.8, 19.1 before 19.1.6, and 19.2 before 19.2.4, which covers self-managed installations as well as the same codebase that powers the GitLab.com SaaS. News reports indicate the flaw came under active exploitation within days of disclosure, and EPSS assigns a 5.8% probability of exploitation within 30 days (93rd percentile). It is not yet listed in CISA's KEV catalog and no public proof-of-concept is known, but defenders should treat it as an actively exploited, unauthenticated, high-impact issue.
    · GitLab CE all versions from 18.2 before 18.11.11, 19.0 before 19.0.8, 19.1 before 19.1.6, and 19.2 before 19.2.4 · GitLab EE all versions from 18.2 before 18.11.11, 19.0 before 19.0.8, 19.1 before 19.1.6, and 19.2 before 19.2.4mass

Appears with

Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.