{"title":"AI developer tools advisories","description":"Advisories for AI coding assistants, agents, MCP servers and AI platforms: prompt injection, leaked keys and poisoned tools.","home":"https://vulnpocalypse.dev/feeds/","items":[{"id":"https://vulnpocalypse.dev/advisories/vibe-coded-apis-ex-hacker-says-they-are-riddled-with-flaws/","title":"Vibe-coded APIs: ex-hacker says they are riddled with flaws","url":"https://vulnpocalypse.dev/advisories/vibe-coded-apis-ex-hacker-says-they-are-riddled-with-flaws/","date":"2026-11-12","summary":"Bank Info Security reports an ex-hacker says vibe-coded APIs are riddled with flaws; details unconfirmed, so review AI-generated API code.","tags":["ai-tools","ai-tools","web"]},{"id":"https://vulnpocalypse.dev/advisories/darktrace-says-stolen-claude-api-keys-can-steer-claude-code-as-implant/","title":"Darktrace says stolen Claude API keys can steer Claude Code as implant","url":"https://vulnpocalypse.dev/advisories/darktrace-says-stolen-claude-api-keys-can-steer-claude-code-as-implant/","date":"2026-11-12","summary":"Help Net Security reports Darktrace showed stolen Claude API keys can steer Claude Code in a lab test; scope and rotate keys.","tags":["ai-tools","ai-tools","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/cyble-says-agentic-ai-can-investigate-phishing-with-human-sign-off/","title":"Cyble says agentic AI can investigate phishing, with human sign-off","url":"https://vulnpocalypse.dev/advisories/cyble-says-agentic-ai-can-investigate-phishing-with-human-sign-off/","date":"2026-11-12","summary":"Cyble says agentic AI can run most of a phishing investigation but warns of hidden prompts in emails; keep a human approving verdicts.","tags":["ai-tools","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/akamai-says-ai-found-bugs-mean-rethinking-exposure-response/","title":"Akamai says AI-found bugs mean rethinking exposure response","url":"https://vulnpocalypse.dev/advisories/akamai-says-ai-found-bugs-mean-rethinking-exposure-response/","date":"2026-11-12","summary":"Akamai published a blog post on AI finding vulnerabilities and rethinking exposure; only the headline was reviewed, so no action is confirmed.","tags":["ai-tools","ai-tools","vuln-data"]},{"id":"https://vulnpocalypse.dev/advisories/chatgpt-shared-link-mathlive-xss/","title":"ChatGPT shared chat link could run attacker code in the victim's session and read private chats (fixed, no","url":"https://vulnpocalypse.dev/advisories/chatgpt-shared-link-mathlive-xss/","date":"2026-11-12","summary":"A public ChatGPT share link could run attacker JavaScript as chatgpt.com and read private chats. OpenAI fixed it on 26 Oct; MathLive users should update.","tags":["ai-tools","ai-tools","web","npm"]},{"id":"https://vulnpocalypse.dev/advisories/cursor-2026-cves/","title":"Cursor 2026 CVEs: DuneSlide sandbox escapes, Git hook and Claude hook RCE, and an unpatched Windows git.exe plant","url":"https://vulnpocalypse.dev/advisories/cursor-2026-cves/","date":"2026-11-12","summary":"Seven 2026 Cursor CVEs let prompt injection or a cloned repo run code outside the sandbox. Update to 3.1.2 or later; the Windows git.exe bug has no stated fix.","tags":["ai-tools","ai-tools","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/lazarus-microsoft-shows-hidden-backdoor-in-ai-agent-model-weights/","title":"Lazarus: Microsoft shows hidden backdoor in AI agent model weights","url":"https://vulnpocalypse.dev/advisories/lazarus-microsoft-shows-hidden-backdoor-in-ai-agent-model-weights/","date":"2026-11-11","summary":"Microsoft researchers showed that editing fewer than 10 neurons can backdoor an AI agent model; verify model provenance and limit agent permissions.","tags":["supply-chain","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/grok-app-builder-35578-public-grokme-apps-expose-data-and-passwords/","title":"Grok app builder: 35,578 public grok.me apps expose data and passwords","url":"https://vulnpocalypse.dev/advisories/grok-app-builder-35578-public-grokme-apps-expose-data-and-passwords/","date":"2026-11-11","summary":"Researchers found 35,578 of 37,571 Grok-built apps open without sign-in, some with passwords; check app access settings and unpublish unowned apps.","tags":["ai-tools","ai-tools","web","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/endor-labs-reports-openclaw-apply-patch-path-traversal-fixed-in-2026214/","title":"Endor Labs reports OpenClaw apply_patch path traversal, fixed in 2026.2.14","url":"https://vulnpocalypse.dev/advisories/endor-labs-reports-openclaw-apply-patch-path-traversal-fixed-in-2026214/","date":"2026-11-11","summary":"Endor Labs reports a path traversal in OpenClaw apply_patch; the project advisory lists a fix in 2026.2.14, so upgrade openclaw.","tags":["ai-tools","npm","nodejs","ai-tools","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/endor-labs-claims-its-ai-sast-found-26x-more-real-flaws-than-claude/","title":"Endor Labs claims its AI SAST found 2.6x more real flaws than Claude","url":"https://vulnpocalypse.dev/advisories/endor-labs-claims-its-ai-sast-found-26x-more-real-flaws-than-claude/","date":"2026-11-11","summary":"Endor Labs claims its AI SAST found 192 real vulnerabilities in an 8-project benchmark; treat it as a vendor claim and test on your own code.","tags":["ai-tools","ai-tools","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/databreachesnet-reports-grok-security-gap-exposed-users-and-musk-secrets/","title":"DataBreaches.net reports Grok security gap exposed users and Musk secrets","url":"https://vulnpocalypse.dev/advisories/databreachesnet-reports-grok-security-gap-exposed-users-and-musk-secrets/","date":"2026-11-11","summary":"DataBreaches.net reports a Grok security blind spot exposed users and Musk company secrets; details are not confirmed, so check official statements.","tags":["ai-tools","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/cloudsek-reports-exposed-silent-lynx-server-tied-to-central-asia-espionage/","title":"CloudSEK reports exposed Silent Lynx server tied to Central Asia espionage","url":"https://vulnpocalypse.dev/advisories/cloudsek-reports-exposed-silent-lynx-server-tied-to-central-asia-espionage/","date":"2026-11-11","summary":"CloudSEK reports an exposed Silent Lynx server tied to Central Asia espionage; defenders there can check logs for the listed IP address.","tags":["ai-tools","enterprise","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/australia-to-mandate-ai-breach-reporting-after-openai-agent-hit-medicare-site/","title":"Australia to mandate AI breach reporting after OpenAI agent hit Medicare site","url":"https://vulnpocalypse.dev/advisories/australia-to-mandate-ai-breach-reporting-after-openai-agent-hit-medicare-site/","date":"2026-11-11","summary":"Australia will make AI firms report breaches after an OpenAI agent accessed a Medicare portal; AI operators should review incident reporting.","tags":["ai-tools","ai-tools","web"]},{"id":"https://vulnpocalypse.dev/advisories/operation-snowball-jailbroken-ai-agent-hits-european-telecom/","title":"Operation Snowball: Jailbroken AI agent hits European telecom","url":"https://vulnpocalypse.dev/advisories/operation-snowball-jailbroken-ai-agent-hits-european-telecom/","date":"2026-11-11","summary":"A jailbroken AI agent attacked a European telecom and 13 hosted organizations for two weeks; patch Cisco BroadWorks CVE-2026-20320 now.","tags":["ai-tools","ai-tools","network-edge","enterprise","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/claude-code-settingslocaljson-leaks-secrets-to-public-github-repos/","title":"Claude Code settings.local.json leaks secrets to public GitHub repos","url":"https://vulnpocalypse.dev/advisories/claude-code-settingslocaljson-leaks-secrets-to-public-github-repos/","date":"2026-11-11","summary":"Claude Code can save approved commands with secrets in .claude/settings.local.json, found in public GitHub repos; rotate any credential it ever held.","tags":["ai-tools","ai-tools","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/claude-dispatch-unpatched-rce/","title":"Anthropic won't fix a Claude Dispatch flaw that lets browser extensions run commands on connected computers","url":"https://vulnpocalypse.dev/advisories/claude-dispatch-unpatched-rce/","date":"2026-11-11","summary":"A browser extension on claude.ai can drive Claude Dispatch to run commands on connected desktops. Anthropic closed it as a duplicate and won't fix it.","tags":["ai-tools","ai-tools","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/openai-gpt6-cyber-948-linux-flaws/","title":"OpenAI's GPT-6 Cyber model generated 948 working Linux kernel root exploits and reported 81 Firefox flaws","url":"https://vulnpocalypse.dev/advisories/openai-gpt6-cyber-948-linux-flaws/","date":"2026-11-11","summary":"OpenAI's GPT-6 Cyber built 948 working Linux kernel root exploits and reported 81 high-severity Firefox flaws, all disclosed for patching.","tags":["ai-tools","ai-tools","open-source","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/artex-ai-framework-exposed-korean-banks/","title":"ARTEX AI pentest operators exposed their own servers, revealing an agentic hacking campaign against South Korean banks","url":"https://vulnpocalypse.dev/advisories/artex-ai-framework-exposed-korean-banks/","date":"2026-11-11","summary":"Operators of the China-made ARTEX AI pentest framework left servers open, exposing Claude Code and DeepSeek-driven tooling tied to breaches at seven South.","tags":["ai-tools","ai-tools","enterprise","cloud","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/workos-artex-ai-breach/","title":"WorkOS says an attacker used the ARTEX AI agent to breach an internal sales app","url":"https://vulnpocalypse.dev/advisories/workos-artex-ai-breach/","date":"2026-11-11","summary":"On 30 October 2026 WorkOS found an attacker had used the ARTEX AI pentest agent to breach an internal sales app and read CRM and customer records.","tags":["ai-tools","ai-tools","enterprise","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/ncsc-warns-ai-powered-ransomware-is-highly-likely-to-hit-uk-critical-infrastruct/","title":"NCSC warns AI-powered ransomware is highly likely to hit UK critical infrastructure by 2028","url":"https://vulnpocalypse.dev/advisories/ncsc-warns-ai-powered-ransomware-is-highly-likely-to-hit-uk-critical-infrastruct/","date":"2026-11-11","summary":"The UK NCSC says AI-powered malware is highly likely to feature in ransomware attacks on critical infrastructure by 2028, so patch and fix the basics now.","tags":["ai-tools","ai-tools","enterprise","php"]},{"id":"https://vulnpocalypse.dev/advisories/llmjacking-google-researchers-report-stolen-ai-access-bills-up-to-1-million/","title":"LLMJacking: Google researchers report stolen AI access bills up to $1 million","url":"https://vulnpocalypse.dev/advisories/llmjacking-google-researchers-report-stolen-ai-access-bills-up-to-1-million/","date":"2026-11-11","summary":"Google researchers report LLMJacking, where stolen cloud credentials run AI models at victim cost; watch AI service changes and rotate keys.","tags":["ai-tools","ai-tools","cloud","enterprise"]},{"id":"https://vulnpocalypse.dev/advisories/3am-ransomware-encrypts-37-machines-in-uk-school-estate-in-suspected-ai-assisted/","title":"3AM ransomware encrypts 37 machines in UK school estate in suspected AI-assisted attack","url":"https://vulnpocalypse.dev/advisories/3am-ransomware-encrypts-37-machines-in-uk-school-estate-in-suspected-ai-assisted/","date":"2026-11-11","summary":"A 3AM ransomware affiliate encrypted 37 machines in a UK school estate in September 2026, with Bitdefender suspecting AI-assisted command retries.","tags":["ai-tools","enterprise","endpoint","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/hugging-face-uploader-claims-leaked-anthropic-numbat-model-checkpoint/","title":"Hugging Face uploader claims leaked Anthropic numbat model checkpoint","url":"https://vulnpocalypse.dev/advisories/hugging-face-uploader-claims-leaked-anthropic-numbat-model-checkpoint/","date":"2026-11-11","summary":"An anonymous Hugging Face uploader claims to share a leaked Anthropic training checkpoint; do not run its bundled custom code outside isolation.","tags":["ai-tools","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/volta-ai-infostealer/","title":"VOLTA infostealer asks an AI which victims are worth robbing, then doxes them from their own Gmail","url":"https://vulnpocalypse.dev/advisories/volta-ai-infostealer/","date":"2026-11-11","summary":"Cisco Talos found VOLTA, a Windows infostealer that grabs credentials, crypto wallets and Gmail data, then asks Claude, Kimi or Gemini to rank the victim.","tags":["ai-tools","endpoint","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/northflank-breach-ai-key-abuse/","title":"Northflank breach leads to abuse of customers' AI API keys \u2014 rotate all secrets","url":"https://vulnpocalypse.dev/advisories/northflank-breach-ai-key-abuse/","date":"2026-11-11","summary":"Northflank disclosed a breach on 30 Oct 2026 after Wiz flagged it; customers report unauthorised AI API key use. Treat all env vars as compromised and rotate.","tags":["ai-tools","cloud","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/solanacry-fake-solana-github-repo-lures-ai-coding-agents-hackread-reports/","title":"SolanaCry: fake Solana GitHub repo lures AI coding agents, Hackread reports","url":"https://vulnpocalypse.dev/advisories/solanacry-fake-solana-github-repo-lures-ai-coding-agents-hackread-reports/","date":"2026-11-11","summary":"Hackread reports a fake GitHub Solana starter kit tells AI agents to install NetSupport RAT; review commands before agents run them.","tags":["supply-chain","ai-tools","open-source","crypto","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/chainalysis-breach-by-offensive-agentic-techniques-exposes-customer-names-and-em/","title":"Chainalysis breach by offensive agentic techniques exposes customer names and emails","url":"https://vulnpocalypse.dev/advisories/chainalysis-breach-by-offensive-agentic-techniques-exposes-customer-names-and-em/","date":"2026-11-11","summary":"Chainalysis says an attacker using offensive agentic techniques accessed customer user IDs, names, emails and role labels, but not investigation content or","tags":["ai-tools","ai-tools","crypto","enterprise"]},{"id":"https://vulnpocalypse.dev/advisories/black-october-ai-platform-breaches/","title":"Black October: nine AI developer platforms breached, stolen keys ran about 2.5M Bedrock calls","url":"https://vulnpocalypse.dev/advisories/black-october-ai-platform-breaches/","date":"2026-11-11","summary":"Nine AI developer platforms disclosed breaches in October 2026. Stolen keys from stored secrets drove about 2.5M Bedrock calls. Revoke, then rotate.","tags":["ai-tools","cloud","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/trojanized-claude-code-extension-21312-21313-on-cursor-marketplace-installs-pers/","title":"Trojanized Claude Code extension (2.1.312, 2.1.313) on Cursor marketplace installs persistent SSH backdoor","url":"https://vulnpocalypse.dev/advisories/trojanized-claude-code-extension-21312-21313-on-cursor-marketplace-installs-pers/","date":"2026-11-11","summary":"A tampered anthropic.claude-code build on the Cursor marketplace planted an SSH key, a reverse tunnel and persistence on up to 5,000 developer machines.","tags":["supply-chain","ai-tools","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/sophos-reports-gold-ogre-used-ai-agents-in-aur0ra-ransomware-intrusions/","title":"Sophos reports GOLD OGRE used AI agents in Aur0ra ransomware intrusions","url":"https://vulnpocalypse.dev/advisories/sophos-reports-gold-ogre-used-ai-agents-in-aur0ra-ransomware-intrusions/","date":"2026-11-11","summary":"Sophos reports the GOLD OGRE group used Cursor and AI models to run Aur0ra ransomware intrusions, so check for its indicators and tighten AD defenses.","tags":["ai-tools","ai-tools","enterprise","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/cursor-claude-code-extension-backdoor/","title":"Trojanized Claude Code extension on Cursor's marketplace planted an SSH backdoor (2.1.312, 2.1.313), plus","url":"https://vulnpocalypse.dev/advisories/cursor-claude-code-extension-backdoor/","date":"2026-11-11","summary":"Fake Claude Code 2.1.312 and 2.1.313 on Cursor's marketplace added an attacker SSH key and reverse tunnel. Check authorized_keys for svc-telemetry.","tags":["supply-chain","ai-tools","endpoint","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/claude-code-extension-cursor-trojanized/","title":"Trojanized Claude Code extension on the Cursor marketplace planted a persistent SSH backdoor","url":"https://vulnpocalypse.dev/advisories/claude-code-extension-cursor-trojanized/","date":"2026-11-11","summary":"A tampered Anthropic.claude-code extension (2.1.312/2.1.313) was live on Cursor's marketplace ~11 hours, planting an SSH backdoor. Rotate keys, remove it.","tags":["supply-chain","ai-tools","endpoint"]},{"id":"https://vulnpocalypse.dev/advisories/google-gemini-4-carbon-security/","title":"Google launches Gemini 4 Carbon, a frontier model it says improves automated vulnerability detection","url":"https://vulnpocalypse.dev/advisories/google-gemini-4-carbon-security/","date":"2026-11-11","summary":"Google released Gemini 4 Carbon (28 Oct 2026), a model it says leads at finding software vulnerabilities, via its limited Fairwind program. Not a breach.","tags":["ai-tools","ai-tools","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/anthropic-ai-model-chained-flaws-into-chrome-safari-android-windows-and-linux-ex/","title":"Anthropic AI model chained flaws into Chrome, Safari, Android, Windows and Linux exploits","url":"https://vulnpocalypse.dev/advisories/anthropic-ai-model-chained-flaws-into-chrome-safari-android-windows-and-linux-ex/","date":"2026-11-11","summary":"Anthropic says an unreleased model chained flaws into five working exploits for Chrome, Safari, Android, Windows and Linux, all reported and patched.","tags":["ai-tools","ai-tools","web","endpoint","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/xint-says-openai-api-compaction-flaw-exposed-hidden-model-reasoning/","title":"Xint says OpenAI API compaction flaw exposed hidden model reasoning","url":"https://vulnpocalypse.dev/advisories/xint-says-openai-api-compaction-flaw-exposed-hidden-model-reasoning/","date":"2026-11-11","summary":"Xint reports an OpenAI API compaction flaw exposed raw model reasoning; per Xint, OpenAI deployed a fix, and no client action is described.","tags":["ai-tools","ai-tools","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/symantec-reports-ai-attack-agent-built-to-hijack-exposed-model-endpoints/","title":"Symantec reports AI attack agent built to hijack exposed model endpoints","url":"https://vulnpocalypse.dev/advisories/symantec-reports-ai-attack-agent-built-to-hijack-exposed-model-endpoints/","date":"2026-11-11","summary":"Symantec reports an AI attack agent built to hijack unauthenticated OpenAI-style endpoints, so require authentication on any model endpoint you expose.","tags":["ai-tools","ai-tools","web","nextjs","cloud","crypto"]},{"id":"https://vulnpocalypse.dev/advisories/railway-breach-rotate-all-environment-variables-and-secrets/","title":"Railway breach: rotate all environment variables and secrets","url":"https://vulnpocalypse.dev/advisories/railway-breach-rotate-all-environment-variables-and-secrets/","date":"2026-11-11","summary":"Railway confirmed attackers may have decrypted customer environment variables; rotate every secret stored there and review provider logs.","tags":["ai-tools","cloud","ci-cd","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/litellm-pypi-docker-compromise/","title":"LiteLLM 1.107.0: poisoned PyPI and Docker release built from a lookalike repository","url":"https://vulnpocalypse.dev/advisories/litellm-pypi-docker-compromise/","date":"2026-11-11","summary":"Attackers with stolen gh CLI tokens shipped malware as LiteLLM 1.107.0 on PyPI, Docker Hub and GHCR. Check before running Python, then rebuild and rotate.","tags":["supply-chain","pypi","ai-tools","ci-cd"]},{"id":"https://vulnpocalypse.dev/advisories/litellm-11070-on-pypi-and-docker-was-backdoored-with-a-credential-stealer-and-re/","title":"LiteLLM 1.107.0 on PyPI and Docker was backdoored with a credential stealer and remote code loader","url":"https://vulnpocalypse.dev/advisories/litellm-11070-on-pypi-and-docker-was-backdoored-with-a-credential-stealer-and-re/","date":"2026-11-11","summary":"LiteLLM 1.107.0 on PyPI and official Docker images ran a credential stealer on every Python start; roll back to 1.106.2 and rotate all reachable secrets.","tags":["supply-chain","pypi","ai-tools","open-source","ci-cd","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/ovhcloud-cli-release-assets-infostealer/","title":"OVHcloud CLI v0.11.0 to v0.15.0: GitHub release binaries and checksums.txt swapped for an infostealer for 94 minutes","url":"https://vulnpocalypse.dev/advisories/ovhcloud-cli-release-assets-infostealer/","date":"2026-11-11","summary":"OVHcloud CLI binaries for v0.11.0 to v0.15.0 fetched on 19 Oct 2026, 12:47 to 14:21 UTC, were an infostealer. Check MD5s, rotate secrets, install v0.16.0.","tags":["supply-chain","cloud","endpoint","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/opencode-console-provider-key-breach/","title":"OpenCode Console breach: OpenAI, Anthropic and Google keys stored in workspaces may have been exposed","url":"https://vulnpocalypse.dev/advisories/opencode-console-provider-key-breach/","date":"2026-11-11","summary":"An intruder reached an OpenCode legacy system and may have exposed provider keys saved in OpenCode Console. Revoke those keys at OpenAI, Anthropic or Google.","tags":["ai-tools","ai-tools","cloud"]},{"id":"https://vulnpocalypse.dev/advisories/crafty-falcon-ai-attacks-indian-nbfcs-payment-apis/","title":"CRAFTY FALCON: CERT-In warns AI-driven attacks are draining Indian BFSI through their own payment APIs","url":"https://vulnpocalypse.dev/advisories/crafty-falcon-ai-attacks-indian-nbfcs-payment-apis/","date":"2026-11-11","summary":"CERT-In advisory CIAD-2026-0058 names CRAFTY FALCON, an AI-assisted actor invoking Indian NBFC and fintech payment APIs to move funds at machine speed.","tags":["ai-tools","ai-tools","enterprise","cloud","web","crypto"]},{"id":"https://vulnpocalypse.dev/advisories/artex-ai-pentest-framework-abused-in-data-theft-from-south-korean-banks/","title":"ARTEX AI pentest framework abused in data theft from South Korean banks","url":"https://vulnpocalypse.dev/advisories/artex-ai-pentest-framework-abused-in-data-theft-from-south-korean-banks/","date":"2026-11-11","summary":"A suspected Chinese-speaking, financially motivated actor used the ARTEX agentic pentest tool to steal data from South Korean financial firms.","tags":["ai-tools","ai-tools","open-source","web","enterprise"]},{"id":"https://vulnpocalypse.dev/advisories/actions-cool-issues-helper-reenabled-malware/","title":"actions-cool/issues-helper and maintain-one-comment came back online still carrying Mini Shai-Hulud malware","url":"https://vulnpocalypse.dev/advisories/actions-cool-issues-helper-reenabled-malware/","date":"2026-11-11","summary":"Hijacked actions-cool/issues-helper and maintain-one-comment were re-enabled on 16 Sep 2026 with every tag still malicious. Remove them and rotate CI secrets.","tags":["supply-chain","github-actions","ci-cd","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/ai-coding-agents-ci-prompt-injection/","title":"AI coding agents in CI: one GitHub issue can reach your secrets","url":"https://vulnpocalypse.dev/advisories/ai-coding-agents-ci-prompt-injection/","date":"2026-11-11","summary":"Prompt injection in GitHub issues let attackers reach CI secrets through Claude Code, Gemini CLI and Codex. Upgrade, and keep untrusted input away from secrets.","tags":["ai-tools","github-actions","ai-tools","ci-cd"]},{"id":"https://vulnpocalypse.dev/advisories/ai-found-vulnerabilities-exploitation-rate/","title":"Mythos-era exploitation statistics: 14 of 1,061 AI-found vulnerabilities exploited, and what Firefox 150's","url":"https://vulnpocalypse.dev/advisories/ai-found-vulnerabilities-exploitation-rate/","date":"2026-11-11","summary":"VulnCheck found 1.3% of AI-found vulnerabilities exploited in 1H 2026, the same as all bugs. Patch AI-found CVEs by exposure, not by how they were found.","tags":["ai-tools","ai-tools","vuln-data","open-source"]},{"id":"https://vulnpocalypse.dev/advisories/teampcp-trivy-litellm-supply-chain/","title":"TeamPCP campaign (CVE-2026-33634): Trivy, KICS, LiteLLM and Telnyx turned into credential stealers","url":"https://vulnpocalypse.dev/advisories/teampcp-trivy-litellm-supply-chain/","date":"2026-11-11","summary":"Poisoned Trivy and KICS actions and images, LiteLLM 1.82.7/1.82.8 and Telnyx 4.87.1/4.87.2 stole CI and developer secrets. Check, then rotate.","tags":["supply-chain","github-actions","pypi","ci-cd","ai-tools"]},{"id":"https://vulnpocalypse.dev/advisories/vulncheck-says-anthropic-glasswing-cves-are-few-fixes-lag/","title":"VulnCheck says Anthropic Glasswing CVEs are few, fixes lag","url":"https://vulnpocalypse.dev/advisories/vulncheck-says-anthropic-glasswing-cves-are-few-fixes-lag/","date":"2026-11-10","summary":"VulnCheck says 442 CVEs trace to Anthropic's Glasswing, 2 exploited; check those two CVEs and treat scanner reports as unverified.","tags":["ai-tools","ai-tools","open-source","vuln-data"]},{"id":"https://vulnpocalypse.dev/advisories/thai-nsc-says-cyberattacks-occur-daily-and-attackers-use-ai-per-report/","title":"Thai NSC says cyberattacks occur daily and attackers use AI, per report","url":"https://vulnpocalypse.dev/advisories/thai-nsc-says-cyberattacks-occur-daily-and-attackers-use-ai-per-report/","date":"2026-11-10","summary":"Asia News Network reports Thai NSC says cyberattack attempts occur daily and attackers use AI; no specific flaw is named, so watch official guidance.","tags":["ai-tools","ai-tools","enterprise"]},{"id":"https://vulnpocalypse.dev/advisories/reversinglabs-reports-ai-linked-malware-signals-rising-no-clear-attack-surge/","title":"ReversingLabs reports AI-linked malware signals rising, no clear attack surge","url":"https://vulnpocalypse.dev/advisories/reversinglabs-reports-ai-linked-malware-signals-rising-no-clear-attack-surge/","date":"2026-11-10","summary":"ReversingLabs says LLM API references in malicious files are rising but no AI attack surge is shown; review exposure to PHP2Shell CVEs.","tags":["ai-tools","ai-tools","php","vuln-data"]}]}