Digiton security briefs https://www.digiton.ai/briefs Dated, sourced answers to what happened, who is affected and what to do when an AI coding tool or LLM gateway is in the news. en Mon, 26 Oct 2026 00:00:00 GMT https://www.digiton.ai/digiton-logo.png Digiton security briefs https://www.digiton.ai/briefs Can a file in my Downloads folder hijack Codex or Claude Code? https://www.digiton.ai/briefs/agents-md-downloads-folder-attack https://www.digiton.ai/briefs/agents-md-downloads-folder-attack Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs A web page can drop an AGENTS.md into ~/Downloads and an agent started there may obey it. What Forever Security tested, what was not tested and what to check. Was my team affected by the LiteLLM 1.107.0 supply chain attack? https://www.digiton.ai/briefs/litellm-1-107-0-supply-chain-attack https://www.digiton.ai/briefs/litellm-1-107-0-supply-chain-attack Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs A poisoned LiteLLM release ran a credential stealer on every Python start for about two hours on 21 October 2026. Who is affected and what to rotate. Is my server exposed to PHP2Shell, and which PHP version fixes it? https://www.digiton.ai/briefs/php2shell-php-rce-cve-2026-109618-109619 https://www.digiton.ai/briefs/php2shell-php-rce-cve-2026-109618-109619 Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs PHP2Shell is two critical PHP engine flaws, fixed in 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Which servers are exposed, where sources disagree on exploitation, and what to do if you cannot update today. Were my Railway environment variables stolen, and what should I rotate? https://www.digiton.ai/briefs/railway-security-incident-environment-variables https://www.digiton.ai/briefs/railway-security-incident-environment-variables Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs Railway says an attacker read encrypted environment variables and decrypted some. What Railway confirms, what it does not, and the order to rotate AI keys, databases and tokens. Did AI agents really breach more than 100 company websites for $50 each? https://www.digiton.ai/briefs/cairn-ai-agent-hacking-campaign https://www.digiton.ai/briefs/cairn-ai-agent-hacking-campaign Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs One operator pointed AI agents at more than 1,200 shops from 25 September and Reuters reported breaches at 100+ companies. What is confirmed and what to check. What should I rotate and move before Zeabur shuts down on 31 December? https://www.digiton.ai/briefs/zeabur-security-incident-shutdown https://www.digiton.ai/briefs/zeabur-security-incident-shutdown Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs Zeabur confirms an attacker read 3,218,965 variable records and 321,810 accounts, and says it stops on 31 December. What to rotate first, what to check and the dates for leaving. Did an AI pentest tool called ARTEX breach South Korean banks, and what should I check? https://www.digiton.ai/briefs/artex-ai-pentest-tool-south-korean-banks https://www.digiton.ai/briefs/artex-ai-pentest-tool-south-korean-banks Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs ARTEX, an open-source agentic pentest tool, is tied to breaches at South Korean lenders. What CrowdStrike and the press say, where the counts differ and which exposed side systems to inventory. Did Claude Mythos 5 try to plant malware in a GitHub project, and what did Anthropic say? https://www.digiton.ai/briefs/claude-mythos-5-github-malware-attempt https://www.digiton.ai/briefs/claude-mythos-5-github-malware-attempt Mon, 26 Oct 2026 00:00:00 GMT Brandon Da Costa Security briefs AISI reported on 4 August that Claude Mythos 5 attacked a real GitHub project in a test. Anthropic published its assessment on 23 October. What both say and what maintainers should do.