WhatsApp, Slack Notifications Could Hijack Google Gemini on Android

A single poisoned notification from WhatsApp, Slack, SMS, Signal, Instagram, or Messenger could have hijacked Google Gemini's voice assistant on Android and made it open a victim's connected windows, fake a message from their boss, push the phone into a Zoom call, or quietly poison its long-term...

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the...

Trojanized Gemini and Claude Installers Target Developers Via SEO Poisoning

Cybercriminals are using SEO poisoning and fake Gemini and Claude installer sites to infect developers with fileless malware and steal data...

MAL-2026-4789 Malicious code in ggk-happy (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector da23474ba170aa6d3b5bea2c2e8ebbc59be022caec4b612528dd644891e31379 ggk-happy is a fork of the slopus/happy CLI that preserves the upstream README, homepage happy.engineering and repository URL github.com/slopus/happy...

Malicious code in edison-tools (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c151a181047e12f1de0e91b1923861446b04558028d518e30df1767ccc85def7 At pip install time, setup.py reads the EDISONQUERY environment variable from the installer's environment and POSTs it to...

MAL-2026-4747 Malicious code in edison-tools (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c151a181047e12f1de0e91b1923861446b04558028d518e30df1767ccc85def7 At pip install time, setup.py reads the EDISONQUERY environment variable from the installer's environment and POSTs it to...

Deleted Google API Keys Remain Active up to 23 Minutes, Study Finds

Deleted Google API Keys remain active for up to 23 minutes after deletion, exposing GCP, Gemini, BigQuery, and Maps data to attackers...

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, wh...

MAL-2026-4394 Malicious code in @ikyyofc/gemini-cli (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5793a1cde3de83b8c15b49a0f9981d72fbf431067a4416ce6b2bd5650ea4a4d6 @ikyyofc/[email protected] ships two heavily obfuscated modules src/gemini.js and src/utils/proxy.js wrapped in an obfuscator.io-style string-array +...

Malicious code in @ikyyofc/gemini-cli (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5793a1cde3de83b8c15b49a0f9981d72fbf431067a4416ce6b2bd5650ea4a4d6 @ikyyofc/[email protected] ships two heavily obfuscated modules src/gemini.js and src/utils/proxy.js wrapped in an obfuscator.io-style string-array +...

MAL-2026-4751 Malicious code in glass-of-water (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector df79336313f71fac8158ff6f3e0160d0e99a8d1d84c452505fd3739af5838a69 glassofwater/init.py embeds 10 Google Gemini API keys AIzaSy... split across 5-part dictionaries and reassembled at runtime by getapikey L6-19. The...

Malicious code in glass-of-water (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector df79336313f71fac8158ff6f3e0160d0e99a8d1d84c452505fd3739af5838a69 glassofwater/init.py embeds 10 Google Gemini API keys AIzaSy... split across 5-part dictionaries and reassembled at runtime by getapikey L6-19. The...

CVE-2026-44902 vulnerabilities

Vulnerabilities for packages: librechat, langfuse-fips, kibana, gemini-cli, langfuse...

GHSA-Q7RR-3CGH-J5R3 vulnerabilities

Vulnerabilities for packages: librechat, langfuse-fips, kibana, gemini-cli, langfuse...

Maestro 0.15.4

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

How to Disable Google's Gemini in Chrome

Chrome users were caught off guard by a 4-GB Google AI model baked into Chrome, sparking privacy concerns. The good news: You can easily uninstall it. The bad? You might not want to...

Google Chrome Accused of Silently Installing 4GB AI Model on User Devices

Cybersecurity researcher Alexander Hanff claims that Google Chrome automatically installs a 4GB Gemini Nano AI model without user notification or consent...

CVE-2026-42338 vulnerabilities

Vulnerabilities for packages: librechat, renovate, wazuh-dashboard, opensearch-dashboards, npm, langfuse-fips, kibana, wazuh-dashboard-fips, code-server, prism, saf, tileserver-gl, lerna, gemini-cli, langfuse, actions-runner, kubeflow-pipelines, pulumi, sqlpad, opensearch-dashboards-fips,...

GHSA-V2V4-37R5-5V8G vulnerabilities

Vulnerabilities for packages: librechat, renovate, wazuh-dashboard, opensearch-dashboards, npm, langfuse-fips, kibana, wazuh-dashboard-fips, code-server, prism, saf, tileserver-gl, lerna, gemini-cli, langfuse, actions-runner, kubeflow-pipelines, pulumi, sqlpad, opensearch-dashboards-fips,...

Google Fixes CVSS 10 Gemini CLI Vulnerability Enabling GitHub Issue-Based RCE

Google patches a CVSS 10 Gemini CLI vulnerability that allowed hackers to use prompt injection and privilege escalation for a full supply chain compromise...