The npm package streak-metricsa version 1.0.0 contains malicious code that drops and executes a native Linux x86-64 ELF binary on any import or require. This binary acts as a remote-command implant using TLS for communication and has capabilities including shell execution and network communication. The package disguises this behavior as a harmless calendar-day math helper, misleading users. Any project importing this package risks executing this implant on the host system.
The streak-day-engine npm package version 1.0.0 contains malicious code that executes immediately upon import or require. It downloads a remote archive, extracts it into the user's AppData directory, and installs a persistent Windows startup script that runs a hidden executable on every user login. This establishes a persistent execution channel controlled by an attacker.
---
_-= Per source details. Do not edit below this line.=-_
## Source: amazon-inspector (5e40aa4b6595789e4ba4b39f82e63526286b36a64ffad2be27536c69c8207590)
src/normalize-options.js is heavily obfuscated (RC4-decoded string array, hex-numeric literals, rotating string-array shuffler, dead-code comparison branches) while the rest of the package (index.js, plugin.js, root.js, declarations.js) is plain readable code. When the PostCSS plugin is instantiated (createPlugin -> normalizeOptions), the loader assembles an HTTPS URL from obfuscated string-array entries, appends keys from the caller-supplied options.features sub-object as query parameters, fetches a JSON response, base64-decodes its `message` field, and executes the decoded code with `new Function('require', code)(require)` — arbitrary code execution in every downstream consumer's build/CI process. The loader also writes a wrapper file to the OS tmpdir (named with process.pid) containing `require('<pkg>')(<options>); setInterval(()=>{},2147483647);` and spawns `process.execPath` detached with stdio ignored and env `LT1_STAGE1_CHILD=1`, then calls `child.unref()`. The detached node child re-enters the loader branch, decoupling the fetch-and-eval from the parent build and keeping it alive on a ~24.8-day interval after PostCSS exits, enabling persistent staging beyond the build window. Package metadata (name postcss-animate-css-vars, description 'PostCSS plugin for animate.css', author 'Alex Rivera <alex@cssanimation.dev>', homepage cssanimation.dev) presents as a legitimate PostCSS ecosystem plugin, but the shipped code contains no animate.css handling in the obfuscated loader path — the metadata is cover for the loader.
## Source: ghsa-malware (28c95517227820c9394897cf41111e5a6992063c2ea1b0f0f9fcb1e530189eac)
Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outside entity, there is no guarantee that removing the package will remove all malicious software resulting from installing it.
Frontier AI is reshaping vulnerability discovery. Learn how our NOVA system found 14,000+ unknown vulnerabilities across the open-source software supply chain. The post The Frontier AI Vulnerability Burst: Industrializing Autonomous Zero-Day Discovery in Open-Source Software appeared first on Unit 42 .
CTI-Transmute contains an uncontrolled resource-consumption vulnerability in the unauthenticated /activity_timeline endpoint. The endpoint accepts a user-controlled days query parameter that was not restricted to a reasonable range.
A remote, unauthenticated attacker could submit an excessively large value for this parameter, causing the application to retrieve and process activity data over an arbitrarily large period. This could consume excessive database, CPU, or memory resources, delay the processing of concurrent requests, or trigger an internal server error. Repeated requests could further degrade the availability of the CTI-Transmute website.
The vulnerability is corrected by clamping the requested timeline range to a minimum of one day and a maximum of 1,095 days.
Hugging Face PyTorch Image Models checkpoint Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face PyTorch Image Models. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file.
The specific flaw exists within the parsing of checkpoints. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current process. Was ZDI-CAN-27987.
Every organization needs security that protects end to end with the speed and scale of AI. Microsoft’s vision is simple: security should be ambient and autonomous, just like the AI it protects. As organizations scale AI and expand across environments, security teams need protection that covers every surface. This month’s updates help security and IT teams secure their AI environments, use AI to defend at speed and scale, and strengthen the foundations that AI-powered operations depend on. Here’s what’s new: Project Perception brings agentic defense to security operations Project Perception , newly announced, is a coordinated system of specialized agents, cybersecurity-focused models, and enterprise-wide signals that transform how security operates. The agents work as a team: red team agents expose weaknesses, blue team agents investigate cyberthreats, and green agents harden what’s found. These multi-agent autonomous workflows work as a team to operate in continuous loops to execute end-to-end security workflows. Learn more about Project Perception Microsoft Defender secures the full AI attack surface, from inbox to cloud Expanded Microsoft Defender protections are designed to reduce risks associated with day-to-day AI interactions, from email inboxes to cloud agent environments. New prompt injection protection in Microsoft Defender, now in preview, identifies and isolates emails containing malicious AI instructions before delivery, reducing the risk of prompt injection attacks reaching the inbox. Unified Defender posture and runtime protection for cloud agents in Microsoft Agent 365 consolidates security posture assessment and runtime protection for Microsoft Foundry, Microsoft Copilot Studio, and third party-managed agents, helping teams reduce AI-specific risk across the agent estate. Accelerate detection, prioritization, and response with AI embedded in SecOps workflows Security teams can accelerate detection, prioritization, and response to cyberthreats with AI embedded directly into security operations (SecOps) workflows through Microsoft Defender. Threat intelligence enhancements, including Microsoft Defender Threat Intelligence convergence and an enhanced Threat Intelligence Agent , bring more out-of-the-box intelligence and automation into the unified SecOps workflow, so teams can move from summary to action. Strengthen the cloud, code, and identity foundations AI depends on Microsoft Defender is strengthening the foundational protections that AI-era operations depend on across cloud, code, and identity. Cloud Security Posture Management extends coverage to serverless containers , giving teams visibility and continuous posture assessment across containerized workloads running on Azure Container Apps, Azure Container Instances, and Amazon Web Services Elastic Container Service (AWS ECS) on Fargate. New interconnected experiences between Defender and Microsoft Entra empower the security operations center (SOC) to disable compromised identities directly using a role-based access control (RBAC) mode that maintains least privilege. Microsoft Defender Experts services are also expanding : Microsoft Defender Experts Threat Intelligence delivers human-led, curated insight into the cyberthreats most relevant to each organization, and Microsoft Defender Experts MDR extends expert-run detection and response beyond the Microsoft estate into third-party and multicloud signals through Microsoft Sentinel . Microsoft Entra strengthens identity across the AI-powered enterprise Strengthen identity foundations for AI-powered operations New capabilities in Microsoft Entra are designed to strengthen the identity foundations that AI-powered operations depend on. Tenant governance helps organizations discover, manage, and govern tenants across their environment with centralized policies and cross-tenant delegated administration. Microsoft Entra ID is making passkeys the default authentication experience , which helps reduce reliance on SMS…
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18300.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18301.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18302.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18303.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18304.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18305.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18306.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18307.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18308.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GIMP. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18309.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GStreamer. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18295.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GStreamer. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18296.
This vulnerability allows remote attackers to execute arbitrary code on affected installations of GStreamer. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-18297.