Close Menu
  • Home
  • News
  • Security
  • Privacy
  • Cybercrime
    • Threat Groups
    • Ransomware
    • Explainers
    • Stealer Logs
  • AI
  • OSINT
  • Tools
    • Ransomtracker
    • Ransomware attacks today
    • Stealercheck
    • FortiBleed Checker
    • Site Check
  • Data
    • Ransomware statistics
    • Ransom payment rate
    • Breach verification
    • Infostealer statistics
  • Newsletter
  • About Us
Facebook X (Twitter) Instagram Threads
Ransomnews
  • Home
  • News
  • Security
  • Privacy
  • Cybercrime
    • Threat Groups
    • Ransomware
    • Explainers
    • Stealer Logs
  • AI
  • OSINT
  • Tools
    • Ransomtracker
    • Ransomware attacks today
    • Stealercheck
    • FortiBleed Checker
    • Site Check
  • Data
    • Ransomware statistics
    • Ransom payment rate
    • Breach verification
    • Infostealer statistics
  • Newsletter
  • About Us
Facebook X (Twitter) LinkedIn
Ransomnews

AI

MACHINE LEARNING

AI

Prompt injection, deepfakes, agentic AI and MCP, security and policy at the frontier.

Where artificial intelligence meets the threat model: prompt injection, agentic and MCP attack surfaces, deepfake-driven social engineering, shadow AI, and the governance rules catching up with all of it. Start with the prompt-injection defender’s playbook, the MCP attack surface and the first AI agent to run a ransomware attack.

Start here

  • Prompt injection: the defender’s playbook
  • MCP security: the attack surface mapped
  • JadePuffer: the first AI agent to run a ransomware attack
  • Deepfake vishing: voice-clone fraud explained

Latest AI security coverage

  • Thieves took bait hidden in AI prompts at three providers: three figures from the Dragos study, 2 million prompts with bait, 3 providers breached and tens of thousands of calls with stolen keys
    Stolen AI prompts: three providers breached, Dragos findsNovember 20, 2026
    Dragos hid trackable secrets in two million AI prompts. They were stolen from three breached providers, read by resellers and fetched despite privacy flags.
  • An AI tool got attackers to admin in under 3 hours: three figures from ARTEX reporting, 5 minutes for the fastest case, more than 2,250 tenants targeted and 1,465 consoles found online
    ARTEX: the AI hacking tool behind the FBI warningNovember 19, 2026
    ARTEX is an AI penetration testing tool the FBI says attackers have used since August 2026. Who used it, how they got in, and what security teams should fix.
  • 36,769 exposed AI endpoints and only 2% behind authentication, ransomnews.com
    36,769 exposed AI endpoints, only 2% ask for a loginSeptember 11, 2026
    Mysterium VPN counted 36,769 self-hosted AI endpoints reachable on the public internet. Only 2.02% return an authentication challenge, and that is a floor.
  • Slopsquatting card showing a terminal where an AI assistant suggests importing a package that does not exist until an attacker registers it, with the stat that 19.7% of AI-generated code named a non-existent package
    What is slopsquatting? AI package hallucinations, explainedSeptember 7, 2026
    Slopsquatting is a supply-chain attack that weaponises the package names AI coding assistants invent. How it works, what the research measured, the real 2026 incidents, and how to defend an AI-assisted pipeline.
  • Delve is dead, the dash took its place. AI lexical markers peak at 0.853 per 1,000 words in 2024 and fall to 0.384 by 2026, while dash usage rises to 0.877, across 21,442 arXiv abstracts.
    “Delve” is dead: AI writing tells expire in 18 monthsAugust 21, 2026
    The word delve fell 94% from its 2024 peak while dash use doubled. We measured 21,442 arXiv abstracts: AI writing tells expire in about 18 months.
  • Vibe coding is shipping vulnerabilities at scale in 2026, ransomnews.com
    Vibe coding is shipping vulnerabilities at scale in 2026July 16, 2026
    AI-generated code is fast and insecure. Veracode found 45% of samples carry OWASP Top 10 flaws, roughly a fifth of AI-suggested packages are hallucinated, and vibe-coded apps are already leaking real data.
  • Prompt injection left the lab in 2026, it is in the wild now, ransomnews.com
    Prompt injection left the lab in 2026. It is in the wild nowJuly 16, 2026
    Prompt injection stopped being a lab demo in 2026. A one-click Claude Desktop flaw, AI browsers leaking credentials, and agents tricked into crypto payments show the attack is now operational, not theoretical.
  • Shadow AI is the new stealer-log jackpot in 2026, ransomnews.com
    Shadow AI is the new stealer-log jackpot in 2026July 16, 2026
    Shadow AI is now a top insider threat: 45% of staff use AI on corporate devices, most via personal accounts. When those sessions land in stealer logs, attackers inherit the AI and everything typed into it.
  • macOS.Gaslight: malware that prompt-injects your SOC, ransomnews.com
    macOS.Gaslight: malware that prompt-injects your SOCJuly 16, 2026
    SentinelLABS found macOS.Gaslight, a DPRK-linked Rust backdoor that embeds 38 fake system messages to make AI malware-triage agents abort. It is the first implant built to attack the analyst’s LLM, not the sandbox.
  • JadePuffer: the first AI agent to run a ransomware attack, ransomnews.com
    JadePuffer: the first AI agent to run a ransomware attackJuly 10, 2026
    Sysdig documented JADEPUFFER, the first ransomware attack whose technical execution was run end to end by an AI agent. A human handler still picked the target, built the infrastructure, and supplied credentials.
  • Agentic AI threats: how MCP becomes an attack chain, ransomnews.com
    Agentic AI threats: how MCP becomes an attack chainJune 29, 2026
    Agentic AI moves the threat from what a model says to what it does. We map how MCP turns goal hijacking, tool misuse, and privilege abuse into a working attack chain, and the controls that contain it.
  • MCP security in 2026: the attack surface mapped, ransomnews.com
    MCP security in 2026: the attack surface mappedJune 28, 2026
    A technical map of the Model Context Protocol attack surface in 2026: tool poisoning, line jumping, rug pulls, tool-chaining exfiltration, token sprawl, and the RCE flaws that turned MCP servers into entry points.
  • Build a secure MCP server in 2026: OAuth 2.1, least privilege, sandboxing, ransomnews.com
    Build a secure MCP server in 2026: a hardening guideJune 27, 2026
    A practitioner’s hardening guide for MCP servers in 2026: OAuth 2.1 auth, least-privilege tool scopes, sandboxing, egress control, and the tool-definition pinning that blocks poisoning and rug pulls.
  • Deepfake vishing 2026 synthwave cover, AI voice-clone fraud, ransomnews.com
    Deepfake vishing 2026: voice-clone fraud explainedJune 24, 2026
    Deepfake vishing uses AI-cloned voices to defeat phone-based trust. Here is how voice-clone fraud works in 2026, what it costs, and how to stop it.
  • Vibrant neon poster: a cracked glowing padlock leaking data with floating cookie, password and US ID icons, title Fable 5 US Only, infostealers vs a US-only AI gate
    Fable 5 and Mythos 5: the US-only gate threat actors will beatJune 15, 2026
    Washington cut Fable 5 and Mythos 5 for every foreigner. Meanwhile 34,814 stolen Claude sessions and 74,114 ChatGPT cookies already sit in infostealer logs. A citizenship gate is just KYC, and KYC loses.
  • Prompt Injection Defender's Playbook 2026 — Ransomnews cover
    Prompt injection: the 2026 LLM defender’s playbookMay 16, 2026
    Prompt injection is now the dominant attack vector against LLM-powered applications, and most teams shipping AI features don’t have a defensive playbook. We map the attack taxonomy, walk through real exploit patterns, and lay out the controls that actually contain the blast radius.
  • AI neural network emitting text streams becoming email envelopes representing LLM-driven phishing
    How large language models are reshaping phishingApril 26, 2026
    Pre-LLM phishing was constrained by language. Post-LLM phishing is not. The result is a measurable upgrade in lure quality, a wider reach into non-English-speaking markets, and an emerging class of personalised attacks that were previously economically unviable.

Every AI article

Every article we have published in this section, newest first.

  • 36,769 exposed AI endpoints, only 2% ask for a login
  • What is slopsquatting? AI package hallucinations, explained
  • “Delve” is dead: AI writing tells expire in 18 months
  • Vibe coding is shipping vulnerabilities at scale in 2026
  • Prompt injection left the lab in 2026. It is in the wild now
  • Shadow AI is the new stealer-log jackpot in 2026
  • macOS.Gaslight: malware that prompt-injects your SOC
  • JadePuffer: the first AI agent to run a ransomware attack
  • Agentic AI threats: how MCP becomes an attack chain
  • MCP security in 2026: the attack surface mapped
  • Build a secure MCP server in 2026: a hardening guide
  • Deepfake vishing 2026: voice-clone fraud explained
  • Fable 5 and Mythos 5: the US-only gate threat actors will beat
  • Prompt injection: the 2026 LLM defender’s playbook
  • How large language models are reshaping phishing

The Ransomnews Monthly

What leaked, what held up

One email a month: the datasets we verified, and the ones that fell apart under scrutiny.

Double opt-in. We store your email, signup time, and IP for consent records (GDPR Art. 7). See our privacy policy.

Free tool

How does your own site score?

Forty passive checks on TLS, security headers, email spoofing and privacy. A grade out of 100 in about fifteen seconds.

No signup. Nothing installed. We only request what your site already serves publicly.

Free tool

Were you in a leak?

Check whether an email address has surfaced in infostealer logs. No signup, no data stored.

Run StealerCheck

Live data

Ransomtracker

Victims as they are posted to ransomware leak sites, tracked continuously and checked against the claims.

Open the tracker

9,760 confirmed attacks tracked

Facebook X (Twitter) LinkedIn
© 2026 Ransomnews.com

Type above and press Enter to search. Press Esc to cancel.

Cookies on Ransomnews

We use strictly-necessary cookies to run the site and may use first-party analytics to understand which articles are read. Some pages contain affiliate links; when you click one, the affiliate network sets cookies on the merchant's domain to attribute the referral. See the Cookie Policy and Affiliate Disclosure for detail.

RANSOMNEWS.COM

Tracking the criminal infrastructure of the internet.

Independent coverage of ransomware, breach economics, threat actors, privacy, AI security, and the open-source investigation toolkit.

Topics

  • News
  • Security
  • Privacy
  • Cybercrime
  • AI
  • OSINT
  • Threat Groups
  • Stealer Logs
  • Ransomtracker
  • Stealercheck
  • FortiBleed Checker
  • Site Check

Site

  • About Us
  • Editorial Team
  • Contact
  • Tip Line
  • Editorial

Legal

  • Privacy Policy
  • Terms of Service
  • Cookie Policy
  • Funding & Independence
  • RSS Feed
© 2026 Ransomnews.com · Tracking the criminal infrastructure of the internet.