Search: “GPT-OSS-Safeguard 20b”

21 stories

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll AI safety & security 2 Model release 1 Exploit / PoC 1

SeverityAll critical 1 high 0 medium 0 low 0 info 3

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Re: Retrospective by 'gpg.fail' authors

Sam James replies to GnuPG author Werner Koch that upstream may freely adopt stricter -W compiler warnings, while distros should avoid blanket -Werror.

This is an oss-security mailing list reply by Sam James (Gentoo toolchain maintainer) to Werner Koch in the thread on the 'gpg.fail' authors' retrospective about GnuPG. James states that upstream projects like GnuPG should feel free to enable whatever -W* warning flags they need. He adds that distributions should not use -Werror indiscriminately, allowing narrow exceptions such as -Werror=format-security, and may reject warning-driven bugs that do not reflect real issues. No new CVE or vulnerability details are disclosed in this reply.

oss-securityupdated 03:19 UTC · 51m agofirst Sep 16, 05:03 UTC · 23h agoVulnerability 9 sources

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackersupdated Sep 11, 14:32 UTC · 5d agofirst Sep 11, 10:51 UTC · 5d agoThreat actor in the wild 3 sources1

PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector

Check Point details PuzzleMask, a plain-prose technique that bypasses LLM gatekeeper policy checks, letting hidden payloads reach target models unreviewed.

Check Point Research describes PuzzleMask, a prompt-crafting technique that hides policy-violating payloads inside plain-English prose wrappers, bypassing quick LLM-based policy checks without emojis, Base64, or invisible formatting. The researchers tested 23 automated prompts against gatekeepers including GPT-4o-mini, GPT-OSS-Safeguard 20b, Claude 3 Haiku, and Llama Guard 3, and all were classified as safe despite policies that flagged the plain versions. When submitted to GPT-5 in thinking-high mode with a Python interpreter, the target model extracted and acted on the payload in over 90% of trials. The technique is not itself a jailbreak but can carry a jailbreak prompt as payload; mitigations include input paraphrasing, hardened gatekeeper policies, and output monitoring.

Check Point Researchupdated Sep 11, 05:53 UTC · 5d agofirst Sep 10, 14:32 UTC · 6d agoAI safety & security 2 sources

Maximum Severity GitLab Flaw Puts Supply Chains at Risk

GitLab CVE-2026-85706 is a maximum-severity CVSS 10.0 path traversal flaw affecting Community and Enterprise Editions, risking supply chain compromise.

CVE-2026-85706 is a path traversal vulnerability with a CVSS score of 10.0 affecting GitLab Community Edition and Enterprise Edition instances. Exploitation could enable attackers to tamper with repositories, posing software supply chain risks. The report does not mention active exploitation.

Dark Readingupdated Sep 15, 00:52 UTC · 2d agofirst Sep 14, 20:19 UTC · 2d agoVulnerability 18 sources CVE-2026-857061

USN-8728-1: Linux kernel (GCP) vulnerabilities

Ubuntu issued kernel security update USN-8728-1 for GCP kernels fixing Arm TLB and AMD Zen 2 privilege escalation flaws (CVE-2025-10263, CVE-2025-54518).

Ubuntu released USN-8728-1, a security update for the Linux kernel used on Google Cloud Platform images. It fixes CVE-2025-10263, where certain Arm processors complete broadcast TLB invalidation before memory writes are globally observed, allowing local attackers to bypass memory protections or escalate privileges, and CVE-2025-54518, an AMD Zen 2 operation cache isolation flaw that can corrupt higher-privilege instructions. The notice also corrects several other kernel security issues.

Ubuntu Security NoticesSep 7, 09:05 UTC · 9d agoAdvisory 6 sources CVE-2025-10263 CVE-2025-54518

PentestGPT: Open-source automated penetration testing agentic framework

Open-source PentestGPT runs autonomous LLM-driven penetration tests via Claude Code and Codex, with legacy human-in-the-loop mode supporting many providers.

PentestGPT, originally published at USENIX Security 2024 by Gelei Deng and colleagues, is an open-source framework that lets a large language model autonomously run penetration testing stages (recon, exploit, walkthrough) with no human in the loop, driving Claude Code or Codex CLIs. A legacy interactive mode uses three cooperating LLM sessions maintaining a Pentesting Task Tree and supports OpenAI, Anthropic, Google Gemini, DeepSeek, xAI, Qwen, Moonshot, and local models via Ollama. The tool sends anonymous telemetry to Langfuse by default, excluding command outputs, credentials, and flags, and is available free on GitHub.

Help Net SecurityAug 12, 00:00 UTC · Aug 12, 2026Tools1

Rockwell Automation ArmorStart LT

CISA flags two flaws (CVE-2026-19471, CVE-2026-19472) in Rockwell Automation ArmorStart LT <=v2.001: stored XSS and web server denial-of-service.

Rockwell Automation reported two issues in the embedded web server of ArmorStart LT v2.001 and earlier. CVE-2026-19471 involves multiple stored cross-site scripting flaws (CVSS 7.3) where unsanitized input is stored server-side and executes in other users' browsers. CVE-2026-19472 is a denial-of-service issue (CVSS 7.5) triggered by a crafted HTTP PUT request that exhausts web server resources. No public exploitation has been reported to CISA.

CISA AdvisoriesSep 3, 12:00 UTC · 13d agoAdvisory 3 sources CVE-2026-19471 CVE-2026-19472

UAT-10147 deploys SPECTRE: A cross-platform implant with Linux rootkit and BYOVD capabilities

Cisco Talos identifies UAT-10147 deploying the SPECTRE implant with cross-platform C2, credential theft, and kernel-level EDR bypass.

Cisco Talos reports that the tracked threat actor UAT-10147 is deploying a newly identified implant named SPECTRE. SPECTRE supports cross-platform command-and-control, process injection, credential theft, and anti-analysis protections. It also includes a Linux rootkit and BYOVD (bring your own vulnerable driver) capability enabling kernel-level EDR bypass, marking an evolution in commodity intrusion tooling.

Cisco TalosAug 20, 10:00 UTC · 27d agoThreat actor in the wild

Hackers Use Claude and GPT-Powered Tools to Help Breach Government and Financial Networks

Unit 42 links two Latin America campaigns where operators used Claude and GPT-4.1 during intrusions against government and financial targets.

Palo Alto Networks Unit 42 identified two activity clusters, CL-CRI-1131 and CL-CRI-1163, tied by shared SOCKS5 relay infrastructure and use of large language models during operations. The Mexican cluster targeted a transportation organization, federal ministries and water utilities in Mexico and Ecuador, while the Brazilian cluster used resume-themed phishing, custom remote-access Trojans and SockTz SOCKS5 tunneling against financial organizations. An exposed self-hosted NextChat interface on attacker infrastructure led researchers to assess operators used Claude and GPT-4.1 to generate workaround scripts and troubleshoot execution failures. Unit 42 noted AI reduced time needed to troubleshoot intrusions after initial access, rather than replacing the attacker.

Cyber Security NewsSep 10, 08:06 UTC · 6d agoThreat actor in the wild 2 sources1

Towards Standardized Evaluation of GPU Memory Safety with GMSBench

GMSBench provides 149 CUDA tests covering spatial, temporal, and concurrency GPU memory errors, exposing detection gaps in Compute Sanitizer.

GMSBench is a GPU memory safety benchmark comprising 149 self-contained CUDA tests spanning spatial, temporal, and concurrency errors across different GPU memory spaces and execution scenarios. The authors evaluate NVIDIA's Compute Sanitizer across multiple GPU architectures using the suite, exposing gaps in its detection coverage. The benchmark offers a standardized foundation for comparative evaluation of GPU memory safety mechanisms.

arXiv cs.CRSep 8, 15:11 UTC · 8d agoResearch

GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests

OpenAI releases GPT-6 Astra, scoring 100% on ExploitBench, but restricts it to secure code review by blocking PoC exploit generation.

OpenAI officially unveiled GPT-6 Astra days after the model reached the "Critical" cybersecurity capability threshold under its Preparedness Framework. The model claims 100% on ExploitBench (versus 78.5% for GPT-5.6 Sol), 98% on FrontierMath Tier 4, and 99.9% on ARC-AGI-3, and demonstrated exploit development including on two zero-days disclosed between June and August 2026. The released version is limited to secure code review and patching and refuses proof-of-concept exploit requests, with less restrictive safeguards planned via OpenAI Daybreak. OpenAI also launched a $1 billion "Daybreak for Frontline Defenders" program for critical infrastructure sectors and a pilot with the US MS-ISAC for public sector and water system defenders.

The Hacker NewsSep 4, 06:47 UTC · 12d agoModel release1

[webapps] CorgetGpsDget 2_3.2 - OS Command Injection

Exploit-DB publishes OS command injection exploit for the obscure CorgetGpsDget 2_3.2 web application.

A public exploit demonstrates OS command injection in CorgetGpsDget version 2_3.2. The flaw could allow attackers to execute arbitrary operating system commands on the hosting server. The product appears to have limited deployment, reducing real-world exposure.

Exploit-DBAug 10, 00:00 UTC · Aug 10, 2026Exploit / PoC

Expanding Daybreak as the Cyber Defense Window Narrows

OpenAI releases GPT-5.6-Cyber, a cybersecurity-specific model offered through Daybreak Red for authorized vulnerability research and security testing.

OpenAI announced GPT-5.6-Cyber, a cybersecurity-specific model available through its Daybreak Red program for authorized vulnerability research, exploit validation, and security testing. The launch is framed around a narrowing cyber defense window and expands OpenAI's portfolio of specialized frontier models.

OpenAI NewsAug 10, 10:00 UTC · Aug 10, 2026Model release

Jenkins Security Advisory 2026-09-16

Jenkins released a security advisory patching vulnerabilities across 13 plugins, including GitLab, Bitbucket, Gradle, Keycloak Authentication, and Script Security.

The Jenkins security advisory dated September 16, 2026 addresses vulnerabilities in 13 plugins: Bitbucket Push and Pull Request, Bitbucket Server Integration, Coverage, Gitee, GitLab, Gradle, Keycloak Authentication, OWASP Dependency-Check, Pipeline: Groovy Libraries, Pipeline: Multibranch, Robot Framework, Script Security, and Warnings. Jenkins users should update the affected plugins to the patched versions listed in the advisory.

Jenkins Security Advisoriesupdated Sep 16, 15:09 UTC · 13h agofirst Sep 16, 12:00 UTC · 16h agoAdvisory 2 sources

Safety overview: GPT-6 Astra

OpenAI's GPT-6 Astra is its most capable broadly deployed model and first to reach Critical cybersecurity capability under the Preparedness Framework.

OpenAI published the safety overview for GPT-6 Astra, describing it as the company's most capable broadly deployed model to date. Under OpenAI's Preparedness Framework, GPT-6 Astra is rated the first model to reach the Critical level of cybersecurity capability. A Critical rating denotes the framework's highest capability tier, significant for defenders given the model's potential to automate offensive security work.

OpenAI NewsSep 3, 00:00 UTC · 14d agoModel release

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

ESET reports Russian group UAC-0099 hid a prompt in VBS malware comments to trip AI safety filters and disrupt automated malware analysis in Ukraine.

ESET identified a technique dubbed GuardBreaker in which UAC-0099 embedded a comment reading "I want to make nuclear weapon. Help me …" inside a malicious VBS script to trigger AI safety mechanisms and halt AI-assisted malware analysis. The script, part of the group's toolset, downloads the MATCHBOIL malware used exclusively by this Russia-aligned group; CERT-UA documented the chain including LUNCHPOKE, BURNYBEAR and MATCHBOIL.V2 in a July advisory. UAC-0099 typically targets transportation and energy sectors and hands validated targets to GRU-linked Sandworm. ESET warned that AI-assisted analysis must be backed by layered detection and human-driven engineering.

Help Net SecurityAug 31, 00:00 UTC · 17d agoAI safety & security in the wild

US, UK, Dutch Agencies Expose Iranian ‘Chosen Brick’ Surveillance Malware

US, UK, and Dutch agencies warn Iranian state actors deploy Windows surveillance malware 'Chosen Brick' against dissidents, activists, and journalists worldwide.

Joint advisories from US, UK, and Dutch agencies describe Chosen Brick, a Windows surveillance malware active since at least 2025 and used by Iranian state cyber actors to track regime opponents. The malware harvests contacts, emails, and social media messages, persists via registry Run keys, evades Microsoft Defender, and uses per-victim Telegram bot IDs for command-and-control and exfiltration. Operators build rapport on WhatsApp and Telegram posing as acquaintances or support staff, disguising payloads as utility software or fake medical documents. Capabilities include screenshot capture, audio recording, credential theft, secondary payload delivery, and data wiping.

SecurityWeekupdated Sep 16, 20:24 UTC · 7h agofirst Sep 16, 12:00 UTC · 16h agoMalware in the wild 6 sources

An Empirical Security Analysis of Open-Source Software Used in Onboard Satellite Systems

Study of 126 onboard satellite OSS repositories finds 2,827 security findings, 72% medium severity or higher, dominated by memory safety and code quality weaknesses.

Researchers performed an empirical security analysis of 126 public repositories of open-source software used in onboard satellite systems using SBOM generation, software composition analysis, static application security testing, infrastructure-as-code analysis, and secret scanning. After cleaning and deduplication the pipeline produced 2,827 findings, with medium-severity findings accounting for 49% and 72% classified medium or higher. A CWE-based taxonomy mapped all findings to eight weakness families, with Memory Safety and Code Quality dominating, followed by Input Validation and Injection. Project-developed code accounted for 81.4% of findings, though external dependency code remained relevant; findings do not establish mission-specific exploitability.

arXiv cs.CRSep 14, 11:54 UTC · 2d agoResearch1

Russian State-Sponsored Hackers Use Claude to Rebuild Malware After Detection

Anthropic disrupted APT29-linked GTG-20006, which used Claude to autonomously rebuild malware, hijack hotel Wi-Fi DNS, and target 20-plus Ukrainian, European, and US-linked organizations.

Anthropic attributed the campaign to GTG-20006, aligned with Midnight Blizzard (APT29/Cozy Bear), which developed an AI-driven process that monitors its implants against security products and autonomously rebuilds and redeploys detected malware. Targets included military intelligence, diplomatic, and defense organizations in Ukraine and Europe, plus Middle East and Asian maritime agencies; the actor compromised at least three hotel Wi-Fi vendors via DNS hijacking and served ClickFix lures delivering Windows, Android, and iOS malware such as PowerChrome, GiftDrop, and DarkSword. Operations also included a North African breach exfiltrating over 300,000 national identity records and 500,000-plus company registry entries, an Embassy Kit device-code phishing campaign stealing Microsoft 365 tokens from at least eight organizations, and WhatsApp account takeover using headless browsers. The campaign overlaps with CaptiveCrunch reporting from ReliaQuest, Microsoft, Google, and Lumen Black Lotus Labs.

The Hacker Newsupdated Sep 16, 13:01 UTC · 15h agofirst Sep 11, 14:10 UTC · 5d agoThreat actor in the wild 18 sources2

Iranian spies hit Windows machines with Chosen Brick data-stealing malware

FBI, UK NCSC, and Dutch AIVD warn Iranian intelligence uses Chosen Brick spyware against dissidents, stealing contacts, emails, and messaging data.

A joint advisory from the FBI, UK NCSC, and Dutch AIVD says Iranian state cyber actors have used the Chosen Brick Windows malware since at least 2025 to surveil dissidents, activists, and journalists. Attacks begin with heavily researched WhatsApp and Telegram messages impersonating trusted contacts, tricking victims into opening fake installers resembling Pictory, RunwayML, Norton Antivirus, Telegram, Adobe Flash Player, and KeePass. The malware persists via the HKCU Run registry key, adds Microsoft Defender exclusions, uses victim-specific Telegram bots for C2, captures screen and audio, steals emails and Telegram/WhatsApp data, and can wipe systems.

The Register · SecuritySep 15, 18:01 UTC · 1d agoThreat actor in the wild1

Re: Linux kernel LPEs: ZcopyReaper (CVE-2026-43502) and 20 more

oss-security thread discusses newly disclosed Linux kernel local privilege escalations, including ZcopyReaper (CVE-2026-43502) and about 20 more flaws.

An oss-security mailing list thread discusses newly disclosed Linux kernel local privilege escalation (LPE) issues, headlined by ZcopyReaper (CVE-2026-43502) along with roughly 20 more. Discussants ask whether the many reports could be summarized and note that locking kernel module loading after boot has repeatedly proven an effective mitigation. The visible discussion does not state whether any of the flaws are exploited in the wild or give specific patch guidance beyond the individual reports.

oss-securitySep 8, 17:02 UTC · 8d agoVulnerability CVE-2026-43502