Fake ChatGPT and Claude apps sideload miners via YobaLoader
Check Point says ZIP files pair signed OpenAI or Anthropic Setup.exe files with a malicious winmm.dll that runs XMRig.
62
Product
OpenAI Codex
- Mentions · 7d2
- Mentions · 30d8
- All mentions16
- First seenAug 17, 2026
- Last mentioned1d ago
Timeline
16 articles · newest firstOWASP: ChatGPT guided a low-skill tester to an admin takeover
On Hack The Box machine Silentium, ChatGPT steered nmap and curl use against a vulnerable Flowise site; autonomous agents did not finish the takeover.
58
Microsoft adds dynamic permissions and risk scores for AI agents
Project Perception now starts agents with minimal access and can isolate or halt high-risk runtimes.
46
Microsoft announces Guardian Agents to constrain AI agent permissions
Discovery now covers 60 local agent types, and risk signals can revoke access or stop an agent.
62
Microsoft extends Project Perception to secure AI agents as insiders
Discovery grows to 60 local agent types, and Entra Agent ID can cover agents found only through sensors.
52
Decepticon – Autonomous Red Team Agent that Integrates Claude and Codex
Open-source Decepticon red team agent links Claude Code and Codex to a LangGraph runtime for scoped attack-path testing.
44
Hackers get $1,262,000 for 98 zero-days at Pwn2Own Ireland
Pwn2Own Ireland 2026 paid $1,262,000 for 98 zero-days, including Galaxy S26, Pixel 10, and OpenAI Codex.
71
Pwn2Own Ireland 2026 - The Full Schedule
ZDI posted the Pwn2Own Ireland 2026 schedule, with over 60 entries including phones and AI targets.
55
MetaPermit: Scalable and Auditable Access Control for AI Agents via LLM-Inferred Meta-Attributes
MetaPermit uses inferred meta-attributes and a fixed policy to authorize AI-agent tool calls more consistently and resist prompt injection.
60
Hackers Deploy Hundreds of AI Agents to Compromise 440 PaperCut Servers
AI-agent campaign exploited PaperCut CVE-2026-81578 and CVE-2026-82078, compromising 440 servers at 395 organizations and reaching Domain Admin in 12.
82
ZDI-26-648: (Pwn2Own) OpenAI Codex External Control of System or Configuration Setting Remote Code Execution Vulnerability
ZDI published a Pwn2Own advisory for CVE-2026-19590, enabling remote code execution in OpenAI's Codex agent via system or configuration control.
52
Is OpenAI Taking Everyone for Fools?
OpenAI faces accusations it scooped NYU mathematicians' Navier-Stokes proof, possibly using their data, amid skepticism about GPT-6 Astra claims.
55
Akeyless adds real-time enforcement for AI agents in production
Akeyless launches Agentic Runtime Authority, enforcing real-time intent-based access control on AI agent actions, with integrations for Claude Enterprise, OpenAI Codex and Amazon Bedrock AgentCore
32
OpenAI's millennium proof dispute raises the question of whether researchers can trust AI labs
Mathematician Tristan Buckmaster accused OpenAI of pressuring him and possibly training on his drafts amid OpenAI's race to claim a Navier-Stokes millennium proof.
48
Coop – Isolated VM Environments for Running Claude Code and Codex
Trail of Bits releases Coop, running Claude Code and OpenAI Codex agents inside isolated virtual machines for safer agentic coding.
28
Hazmat: Open-source containment for AI agents
Open-source tool Hazmat runs AI coding agents like Claude Code and Codex in a dedicated account, restricting access to credentials and files.
22
Related CVEs
by mentions- CVE-2026-8207861%9.4Unsafe Reflection RCE in PaperCut NG/MF, Chained with Auth Bypass in Attacks
- CVE-2026-8157884%8.8Missing Authentication for Critical Function in PaperCut NG/MF Web Interface
- CVE-2021-4228777%7.5Privilege Escalation in Microsoft Active Directory Domain Services
- CVE-2021-4227873%7.5Privilege Escalation via sAMAccountName Spoofing in Microsoft Active Directory
- CVE-2026-19590<1%7.3Unsandboxed Git Hook Execution (CWE-427) in OpenAI Codex Desktop
Appears with
- OpenAIvendor · 10
- Claude Codeproduct · 8
- Anthropicvendor · 4
- Microsoftvendor · 3
- Zero Day Initiativeorganization · 3
- OpenAI Codexai model · 3
- GitHub Copilotproduct · 3
- Project Perceptionproduct · 3
- Googlevendor · 2
- OpenAIorganization · 2
- Viettel Cyber Securityorganization · 2
- Microsoft Agent 365product · 2
- Oraclevendor · 2
- Microsoft Entra Agent IDproduct · 2
- Samsungvendor · 2
- Garminvendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.