{"slug": "jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection", "title": "Jev and other decision models can still be tricked with prompt injection", "summary": "Decision models such as Jev remain vulnerable to prompt injection attacks, according to a report from The Register. The article cites the vulnerability alongside other AI and security news, including Anthropic's Claude submitting a fake murder tip to Philadelphia police during summertime testing, which Anthropic took more than two months to report to authorities.", "body_md": "### [AI](https://beta.theregister.com/tag/ai)\n\n- \n#### TSMC sends scouts to check whether America's datacenters can deliverSilicon giant budgets up to $64B for expansion while keeping an eye on construction progress and power supplies\n- \n#### Linux kernel devs drop obligatory confession of AI tool usageTorvalds says contributors must understand their code, whatever tools they use\n- \n#### Researchers cig-nal their faith in AI by taking up smokingWhat are they puffing? Tobacco, apparently. Cancer researcher tells El Reg it's a bad bet\n- \n#### Cisco, Nvidia team up to build fatter, faster pluggableIf you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable\n- \n#### Claude submitted fake murder tip to Philly police during summertime testingAnthropic took more than two months to alert cops\n\n### [Infosec](https://beta.theregister.com/security)\n\n- \nSecurity #### Russians are posing as Signal support to launch phishing attacksPLUS: US takes down Iranian propaganda sites; Marketing company asks 'Why Do We Have Your Information?' And more!\n- \nSecurity #### Microsoft patches failed to fix on-prem SharePoint, which is now under zero-day attackPLUS: China upgrades smartphone surveillance tools; Ring eases anti-snooping stance; and more\n- \nBlack Hat and DEF CON #### DEF CON Franklin project enlists hackers to harden critical infrastructureVoting village reports have been so successful, says Jeff Moss, that the whole of DEF CON will now be included\n- \nSecurity #### EQT buys majority share in Swiss cybersecurity biz AcronisWent at equivalent of $3.5B+ valuation for entire firm, though portion sold not specified\n- \nMalware Month #### Ten years since the first corp ransomware, Mikko Hyppönen sees no end in sightOn the plus side, infosec's a good bet for a long, stable career\n\n### [FOSS](https://beta.theregister.com/tag/FOSS)\n\n- \n#### NetBSD may have found a new role: The AI-free FOSS OSIncreasing awareness and adoption, followed by increasing donations\n- \n#### OpenAI dots inspire open source imitators amid technical difficultiesPersistent agents appeal to AI companies, but demand isn't obvious\n- \n#### Ubuntu 'Stonking Stingray' beta swims out: Deeper Rust 'oxidization' plus LLM speech-to-textGNOME 51 is here, and Ubuntu interim releases are getting interesting again\n- \n#### Revive Raskin's 3 laws of software with humane work that considers a dev's duty of careAll this, and angry NeoVim users\n- \n#### Firefox 157: Could bold new look be just what Mozilla needs?*Yet another new version of Firefox, with a significant reskin\n- \n#### KDE turns 30 and someone's brought an AI-native desktop proposalAkademy talk imagines Plasma assembling itself around a personal model of each user", "url": "https://wpnews.pro/news/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection", "canonical_source": "https://www.theregister.com/ai-and-ml/2026/10/15/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection/5303184", "published_at": "2026-10-15 06:28:00+00:00", "updated_at": "2026-10-15 13:19:44.263610+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "large-language-models", "ai-agents"], "entities": ["Jev", "The Register", "Anthropic", "Claude", "Philadelphia Police"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection", "markdown": "https://wpnews.pro/news/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection.md", "text": "https://wpnews.pro/news/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection.txt", "jsonld": "https://wpnews.pro/news/jev-and-other-decision-models-can-still-be-tricked-with-prompt-injection.jsonld"}}