Issue 53 · Nov 16–22, 2026Agent Age News magazine · Other editions · Search · Method · HU / ENG

Incidents and influence attempts in the age of agents

Issue 34

Jul 6–12. 2026 · 37 stories · 2 of them Hungarian and regionalPage last updated: Nov 21, 2026
Viewpoint

incident · global

Sysdig: AI agent carries out ransomware attack, but 'no human help' claim is disputed

Sysdig researchers say an AI agent called JADEPUFFER carried out a complete ransomware attack in 31 seconds by exploiting Langflow vulnerability CVE-2025-3248 (2026-07-06). Other reports say the "first" AI-driven attack still required human involvement.

2026. Jul 6. · 11 sources

Who is affected and how

security leader
The researchers say the attack chain runs at machine speed, so defence plans built on human reaction time need to be rethought.
security operations
Because an instance exploiting Langflow CVE-2025-3248 was involved, exposed Langflow deployments should be checked.
developer
For systems built on Langflow, the concrete tasks are patching CVE-2025-3248 and assessing how exposed instances are.
journalist and researcher
The "fully autonomous" label is disputed, so Sysdig's claim should be reported together with a precise description of the human role.
vulnerability · United States

CISA adds Adobe ColdFusion and Oracle Agile PLM flaws to its Known Exploited Vulnerabilities catalog

On 2026-07-06, CISA added vulnerabilities in Adobe ColdFusion and Oracle Agile PLM to its Known Exploited Vulnerabilities catalog. Another report says the maximum-severity ColdFusion flaw is already…

security leaderThe listing sets a patching-deadline priority for risk management.security operationsCatalog listing signals exploitation, so patching ColdFusion and Oracle Agile PLM instances should be prioritised.
research · global

GitLost: prompt injection flaw lets GitHub's AI agent leak private repository contents

Noma Labs says a prompt injection flaw called GitLost caused GitHub's AI agent to expose private repository data after a specially crafted public issue. The researchers say the safeguards were also…

security operationsThe permissions of agents connected to code repositories and their data exfiltration paths should be reviewed.developerAI agents with access to private repositories should be treated as attackable through public issues and other untrusted inputs.journalist and researcherNoma Labs' write-up is a concrete example of prompt injection affecting source code.
jelentés · Egyesült Királyság

UK agency: GPT-5.6 jailbreaks unlock dangerous cyber capabilities

A UK agency has found that jailbreaks of OpenAI's GPT-5.6 model unlock dangerous cyber capabilities (2026-07-10).

security leaderModel safeguards can be bypassed, so attacker capabilities must be factored into threat modelling.public-sector decision-makerThe result of government testing supports cybersecurity evaluation of frontier models.journalist and researcherThe agency's finding underlines the importance of measuring jailbreak resistance.
vulnerability · United States

CISA warns of active exploitation of SharePoint remote code execution flaw

On 2026-07-06, CISA warned that a SharePoint RCE vulnerability is being actively exploited.

security leaderBased on the agency warning, an emergency patching decision covering SharePoint is justified.security operationsGiven the active exploitation, patching SharePoint servers and checking their exposure is urgent.

Hungary

More key stories of the week

regulation · United Kingdom

M&S, Nationwide, Microsoft and ITV sign UK government's voluntary cyber resilience pledge

On 2026-07-06, DSIT and the NCSC launched the voluntary Cyber Resilience Pledge. Reports say there are more than 60 founding signatories, including M&S, Nationwide, Microsoft and ITV.

security leaderThe pledge may become a new benchmark for assessing security programmes and for supplier expectations.business leaderThe voluntary pledge is a public commitment to cyber resilience.
regulation · European Union

European Commission refers Ireland, Spain, France and Netherlands to EU Court of Justice over cybersecurity rules

On 2026-07-07, the European Commission referred Ireland, Spain, France and the Netherlands to the Court of Justice of the EU for failing to transpose the cybersecurity rules.

business leaderFor companies operating in the four countries, uncertainty over national rules affects compliance planning.public-sector decision-makerThe procedure shows that transposition delays can be enforced at EU level.
regulation · European Union

EU presents action plan on cybersecurity risks and opportunities of advanced AI

On 2026-07-07 the European Commission presented an action plan to address the cybersecurity risks and opportunities of advanced artificial intelligence. A Hungarian-language report on it has also…

security leaderThe action plan signals the EU's direction on defensive and offensive uses of AI.public-sector decision-makerThe plan gives an EU framework for managing the cybersecurity risks of AI.
bűnüldözés · Ázsia

Japanese police arrest teenager over ChatGPT-assisted attack on anime and Bandai Channel accounts

Japanese police arrested a 15-year-old boy, according to reports of 2026-07-06, over a cyberattack that unsubscribed more than 46,000 anime accounts. Reports say the attack was assisted by ChatGPT…

security operationsDetecting and limiting mass automated actions against accounts is a defensive task for service providers.journalist and researcherThe case is an example of entry-level attacks supported by AI tools.
incident · global

Fake Paysafe and Skrill SDKs on npm and PyPI steal credentials

Fake Paysafe and Skrill SDK packages have appeared on npm and PyPI and steal credentials (2026-07-08).

security operationsIn build environments, dependency sources should be checked and credentials rotated if an affected package was pulled in.developerPackage names and publishers of payment SDKs should be verified before installation.
research · global

Huntress analyzes vibe-coded malware used to map Active Directory environments

An analysis published on 2026-07-08 examines an AI-generated, vibe-coded malicious tool for Active Directory enumeration.

security operationsDetecting Active Directory enumeration is a defensive task regardless of where the tool came from.journalist and researcherThe analysis offers a concrete sample of AI-assisted malware development.
vulnerability · global

Microsoft patches RoguePlanet zero-day in Defender

According to reports on 2026-07-09, Microsoft took action to contain the zero-day threat known as RoguePlanet.

security leaderHandling the zero-day calls for a case-by-case risk assessment.security operationsFollowing Microsoft's action, the relevant updates and mitigations should be verified.
incident · European Union

Dutch police suspect Dutch hackers were involved in Odido data breach

Police said on 2026-07-10 that they suspect Dutch hackers were involved in the Odido data breach.

security leaderThe police suspicion shows the direction of investigations into service-provider data breaches.citizenThe breach puts the personal data of affected customers at risk, so notifications from the provider should be monitored.
research · global

Prompt injection attacks can trick AI agents into making crypto payments

A report on 2026-07-06 says prompt injection attacks can be used to trick AI agents into making crypto payments.

security leaderFor agents able to move funds, deceptive inputs pose a direct risk of financial loss.developerAgents with payment authority should be protected with approval steps and value limits.
bűnüldözés · Európai Unió

Spain arrests suspect linked to pro-Russian hacktivist groups in operation with the FBI

Spain's Interior Ministry said the National Police, working with the FBI, arrested an alleged collaborator of the pro-Russian hacktivist groups CyberArmy of Russia Reborn (CARR) and Z-Pentest (7 July…

security leaderThe Western law-enforcement cooperation is an example of action against hacktivist groups.journalist and researcherThe official statement describes the suspect's link to the groups as alleged.
attribution

New Iran-linked group targets Israeli government and IT sectors

According to Infosecurity Magazine, a new Iran-linked hacker group is targeting Israeli government and IT organisations (2026-07-06).

security leaderThe campaign against Israel's government and IT sectors is part of the regional threat picture.journalist and researcherAccording to the report, the Iran link is an attribution, not an established fact.
research · global

HalluSquatting: AI coding assistants can be tricked into installing botnet malware

According to a report of 2026-07-08, an attack called HalluSquatting can trick AI coding assistants into installing botnet malware.

security operationsPackages suggested by AI that enter the development environment need to be verified.developerPackage names and dependencies suggested by an AI assistant must be checked before installation.

In brief

incidentAssuranceAmerica data breach exposes records of 6.9 million driverscitizenThe personal data of the affected drivers is exposed, which raises the risk of identity theft.incidentInsurance Business: Russian hackers offering UK government logins from FortiBleed breach for salesecurity operationsThe tasks are to replace credentials linked to FortiBleed and to review access logs.public-sector decision-makerThe exposure of government and council accounts, through data appearing on the public market, is a risk.incidentAccenture confirms data breach after hacker offers stolen data for salesecurity leaderOrganisations with ties to Accenture should clarify whether they are affected.business leaderThe breach at a client-services provider highlights the need to manage supplier risk.researchDEBULL tooling abuses Microsoft device-code flow to target M365 accountssecurity leaderReassessing the risk of M365 authentication flows is warranted.security operationsMonitoring and restricting use of the device-code flow in M365 environments is a defensive step.incidentDeutsche Bank confirms third-party breach as ransomware gang claims access to internal datasecurity leaderThird-party access increases the exposure of bank data, so supplier security must be checked.business leaderThe case also raises questions of responsibility within the supply chain.researchThousands of malicious AI skills found that can steal data and run malwaresecurity operationsControlling which AI skills are allowed and isolating their runtime environment are defensive measures.developerThird-party skills installed for agents should be used only with source verification and permission limits.reportEuropean supervisory authorities back ESRB warning on systemic cyber risks from frontier AI modelssecurity leaderFinancial supervisors treat advanced AI as a systemic risk, which affects the sector's security risk assessments.public-sector decision-makerThe supervisory position is a regulatory consideration for the link between financial stability and AI.influence operationAgency warns of Russian disinformation around Berlin electionpublic-sector decision-makerThe warning bears on preparedness against election disinformation.journalist and researcherThe Russian origin is the agency's claim; the communication does not state the activity's impact.reportCertiK: crypto hacks fell 47% in first half of 2026security leaderDespite the decline, CertiK says risk remains significant for organisations that handle crypto assets.journalist and researcherCertiK's figure is a single-source industry measurement and can be reported with attribution.caseJudge approves $46.75 million payout for 23andMe data breach victimsbusiness leaderThe ruling shows the financial consequences of data breaches.citizenThose affected can expect compensation.incidentPeckshield: $5.25 million drained from Hedera and bridged to Ethereum in suspected exploitsecurity leaderThe withdrawal through a bridge highlights the bridging risk of crypto assets.journalist and researcherThe incident is a suspected exploit; Peckshield's statement is not yet independent confirmation.incidentRansomware attack hits Mount Royal University; student and employee data compromisedcitizenStudent and staff data are affected, so it is worth following the privacy notification.toolUK plans autonomous AI-powered 'Cyber Shield' to defend the countrysecurity leaderDeploying autonomous defence systems points to future changes in SOC workflows.public-sector decision-makerThe plan signals the use of autonomous AI in state defence.researchGhost phishing campaign targets Microsoft 365 users with encrypted browser pagessecurity operationsThe task is to detect and block phishing pages aimed at M365 users.citizenThe authenticity of M365 sign-in pages must be verified.fraudWoman loses a year's savings to AI deepfake scam on dating sitecitizenAI-generated impersonation can also occur on dating sites, so any request for money should always be verified.caseBlock settles with states over Cash App fraud protections for $45 millionbusiness leaderGaps in fraud protection carry regulatory and financial consequences.citizenLive customer support can help victims of fraud.vulnerabilityChrome 150 update patches 27 vulnerabilitiessecurity operationsUpdating the browser fleet is timely, before the fixed flaws can be exploited.regulationCISA targets September for release of data breach reporting rulesecurity leaderThe reporting requirement may affect incident response processes at organisations with US exposure.business leaderThe new rule may create a legal compliance task.

← Issue 33 · Issue 35 →

Weekly email

One email a week with the main stories from the Agent Age editions. You confirm by email and can unsubscribe in one click.

Almost done: we sent you an email. Open it and press the confirm link. If it does not arrive within a few minutes, check your spam folder.