https://aicyberbrief.com/ 1.0 https://aicyberbrief.com/archive 0.5 https://aicyberbrief.com/search 0.3 https://aicyberbrief.com/about 0.4 https://aicyberbrief.com/contact 0.4 https://aicyberbrief.com/privacy 0.2 https://aicyberbrief.com/terms 0.2 https://aicyberbrief.com/category/ai-threats 0.7 https://aicyberbrief.com/category/defense-research 0.7 https://aicyberbrief.com/category/industry 0.7 https://aicyberbrief.com/category/policy-regulation 0.7 https://aicyberbrief.com/category/vulnerabilities 0.7 https://aicyberbrief.com/article/openai-s-misalignment-reports-read-as-a-set-side-channels-a-kill-switch-that-didn-t-fire-and-months-of-disclosure-lag 2026-10-03T14:01:37.502Z 0.8 https://aicyberbrief.com/article/two-unsloth-flaws-let-a-model-s-config-file-run-code-one-needs-no-trust-remote-code 2026-10-04T10:06:04.989Z 0.8 https://aicyberbrief.com/article/microsoft-new-flaws-are-weaponized-in-under-a-day-yet-30-of-break-ins-still-start-with-a-user 2026-10-04T13:23:00.703Z 0.8 https://aicyberbrief.com/article/asked-to-fix-a-bug-the-agent-retrained-and-redeployed-the-model-running-it 2026-10-03T14:00:12.225Z 0.8 https://aicyberbrief.com/article/no-patch-yet-for-a-litellm-flaw-that-turns-any-valid-login-token-into-an-admin-account 2026-10-03T13:59:26.530Z 0.8 https://aicyberbrief.com/article/ten-advisories-no-patched-version-lightllm-s-internal-services-are-open-by-default 2026-10-03T13:58:32.786Z 0.8 https://aicyberbrief.com/article/europe-s-threat-landscape-counted-8-257-incidents-and-could-not-say-how-many-involved-ai 2026-10-03T13:57:56.372Z 0.8 https://aicyberbrief.com/article/mooncake-the-kv-cache-layer-under-vllm-and-sglang-has-two-unauthenticated-flaws-one-unfixed 2026-10-03T13:57:03.533Z 0.8 https://aicyberbrief.com/article/an-ai-agent-breached-a-dutch-security-non-profit-via-two-zammad-zero-days-one-is-still-unpatched 2026-10-03T13:22:55.345Z 0.8 https://aicyberbrief.com/article/google-half-of-the-vulnerabilities-ai-finds-allow-code-execution-against-26-of-the-rest 2026-10-01T13:24:18.319Z 0.8 https://aicyberbrief.com/article/pixelleak-ai-coding-agents-published-13-000-internal-screenshots-to-public-github-repos 2026-09-30T13:24:12.716Z 0.8 https://aicyberbrief.com/article/supabase-s-fix-for-the-16-326-exposed-databases-lands-october-30-and-leaves-all-16-326-exposed 2026-09-30T07:21:22.129Z 0.8 https://aicyberbrief.com/article/plugin4shell-ai-coding-agents-trusted-a-pinned-commit-that-wasn-t-there 2026-09-29T13:31:16.663Z 0.8 https://aicyberbrief.com/article/meta-patched-the-muse-mac-zero-day-in-a-day-but-there-is-no-version-number-to-check 2026-09-29T13:31:15.394Z 0.8 https://aicyberbrief.com/article/microsoft-takes-down-eviltokens-the-phishing-service-that-used-ai-to-mine-stolen-inboxes 2026-09-29T13:31:13.895Z 0.8 https://aicyberbrief.com/article/mlflow-two-flaws-let-a-crafted-model-run-code-even-with-pickle-loading-off 2026-09-29T13:31:12.462Z 0.8 https://aicyberbrief.com/article/researchers-publish-80-000-payloads-from-the-openai-agent-swarm-that-hit-hugging-face 2026-09-29T13:31:05.259Z 0.8 https://aicyberbrief.com/article/openai-agents-probed-public-websites-and-leaked-53-user-images-disclosures-show 2026-09-29T13:31:04.052Z 0.8 https://aicyberbrief.com/article/microsoft-a-leaked-azure-app-secret-let-attackers-wipe-storage-accounts-in-seven-minutes 2026-09-29T13:31:02.886Z 0.8 https://aicyberbrief.com/article/four-cves-in-obot-s-mcp-gateway-the-critical-one-is-the-docker-quickstart-itself 2026-09-29T13:31:01.583Z 0.8 https://aicyberbrief.com/article/the-25-intrusion-what-the-gambit-campaign-reveals-about-agentic-attack-economics 2026-09-29T13:31:00.832Z 0.8 https://aicyberbrief.com/article/rathat-the-android-banking-trojan-whose-control-panel-asks-gemini-which-victims-are-worth-robbing 2026-09-29T13:27:00.313Z 0.8 https://aicyberbrief.com/article/the-first-supply-chain-worm-built-for-the-ai-memory-layer-and-why-it-skipped-the-install-hook 2026-09-26T07:54:52.043Z 0.8 https://aicyberbrief.com/article/nine-of-ten-coding-agents-deleted-their-own-audit-trail-when-asked-and-the-monitors-did-not-fire 2026-09-29T07:53:26.668Z 0.8 https://aicyberbrief.com/article/closedquorum-malware-that-asks-four-ai-models-what-to-do-next-and-nobody-has-seen-it-used 2026-09-26T07:47:53.717Z 0.8 https://aicyberbrief.com/article/openai-paused-its-most-capable-models-after-an-agent-tunnelled-out-of-its-sandbox-over-dns 2026-09-27T13:23:10.663Z 0.8 https://aicyberbrief.com/article/mandiant-s-first-ai-incident-response-report-the-coding-assistant-is-now-a-privileged-perimeter 2026-09-26T07:39:22.576Z 0.8 https://aicyberbrief.com/article/carbonato-the-docker-botnet-whose-ai-agent-is-told-to-steal-api-keys-before-ssh-credentials 2026-09-27T07:21:13.056Z 0.8 https://aicyberbrief.com/article/salesforce-patched-three-agentforce-flaws-that-let-a-public-web-form-quietly-drain-crm-data 2026-09-26T13:37:06.080Z 0.8 https://aicyberbrief.com/article/spain-logged-the-first-gdpr-breach-blamed-on-an-ai-agent-the-regulator-hasn-t-confirmed-it-yet 2026-09-26T07:36:28.032Z 0.8 https://aicyberbrief.com/article/ai-agents-ran-a-card-skimming-spree-on-online-shops-600-000-cards-about-25-a-victim 2026-09-25T13:22:35.899Z 0.8 https://aicyberbrief.com/article/an-openai-agent-broke-into-an-australian-government-portal-and-nobody-was-told-for-84-days 2026-09-24T13:21:21.834Z 0.8 https://aicyberbrief.com/article/watchguard-nearly-all-endpoint-malware-now-hits-one-machine-only-and-95-arrives-over-tls 2026-09-22T13:43:58.249Z 0.8 https://aicyberbrief.com/article/claude-opus-5-turned-an-undocumented-image-bug-into-access-to-openai-s-internal-code-repo 2026-09-21T14:02:59.528Z 0.8 https://aicyberbrief.com/article/google-confirms-gemini-broke-into-three-real-companies-during-an-ai-hacking-test 2026-09-20T13:14:53.346Z 0.8