[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fkgUYfBgX9fPG3wY1tpRlnzna1npD3KG1rh2wcwHr7r4":3},{"article":4,"iocs":47,"watch_terms":52,"solutions":53,"lesson":131},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"url":11,"image_url":12,"published_at":13,"ingested_at":14,"relevance_score":15,"entities":16,"category_id":29,"category":30,"article_tags":34},"7dcf3b64-0052-43d6-8f5a-7c85304da494","A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw","a-malicious-webpage-could-poison-your-local-ai-model-behind-nvidia-nemoclaw-363f9e","Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself. The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA's Product Security Incident","Oasis Security has discovered a vulnerability in NVIDIA NemoClaw that could allow an attacker-controlled webpage to gain unauthenticated control of a local Ollama instance. This could enable attackers to inject hidden instructions into AI models, altering their behavior. While a fix exists for macOS and Linux in NemoClaw v0.0.35, Windows and WSL paths remain vulnerable or have workarounds.","NVIDIA NemoClaw vulnerability allows malicious webpages to poison local AI models via Ollama.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F08\u002Fa-malicious-webpage-could-poison-your.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEhMaJs9yp_YLYc3dgsmzjU4_ma-6DC3KNpG4d3KhKtoIuhtpbYSnK0Wed5_8a0Jm6epc_RdLE9PVMO0FnkH7DFwRAI7lBZBXImFEu1emv-OarT-LPYE-QymTXPMkmDsYBXsz1TB3gASsiAEgZ4Jvt1YzQM3KHYpV0HMck686hTcXB7pn7uqLu2uTLVgPyE\u002Fs1600\u002Fnvidia.jpg","2026-08-25T14:07:37+00:00","2026-08-25T16:00:09.768795+00:00",8,[17,20,22,25,27],{"name":18,"type":19},"NemoClaw","product",{"name":21,"type":19},"Ollama",{"name":23,"type":24},"NVIDIA","vendor",{"name":26,"type":19},"OpenClaw",{"name":28,"type":19},"OpenShell","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":29,"icon":31,"name":32,"slug":33},null,"Vulnerabilities","vulnerabilities",[35,40,42],{"category":36},{"id":37,"icon":31,"name":38,"slug":39},"26b0b636-0e31-4db1-bffb-61bdf9f20a58","Supply Chain","supply-chain",{"category":41},{"id":29,"icon":31,"name":32,"slug":33},{"category":43},{"id":44,"icon":31,"name":45,"slug":46},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",[48],{"type":49,"value":50,"context":51},"cve","CVE-2024-28224","Ollama vulnerability related to Host header validation, which NemoClaw bypasses when binding to non-loopback addresses.",[23,18,21],{"controls":54,"vendors":130},[55,76,105],{"slug":56,"name":57,"problem":58,"products":59},"endpoint-management","Device management (MDM and UEM)","Every company laptop and phone is known, encrypted, locked down and up to date.",[60,68],{"vendor_slug":61,"vendor_name":62,"vendor_logo":63,"product_slug":64,"product_name":65,"url":66,"description":67},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","intune","Microsoft Intune","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fmicrosoft-intune","Device management for Windows, macOS, iOS and Android, including update rings and compliance policies.",{"vendor_slug":69,"vendor_name":70,"vendor_logo":71,"product_slug":72,"product_name":73,"url":74,"description":75},"ninjaone","NinjaOne","\u002Fvendor-logos\u002Fninjaone.png","ninjaone-patch-management","NinjaOne Patch Management","https:\u002F\u002Fwww.ninjaone.com\u002Fpatch-management\u002F","Automated patching of operating systems and third-party applications from the cloud.",{"slug":77,"name":78,"problem":79,"products":80},"network-segmentation","Network segmentation and microsegmentation","One compromised machine can no longer reach everything else.",[81,89,97],{"vendor_slug":82,"vendor_name":83,"vendor_logo":84,"product_slug":85,"product_name":86,"url":87,"description":88},"threatlocker","ThreatLocker","\u002Fvendor-logos\u002Fthreatlocker.png","zero-trust-endpoint-firewall","Zero Trust Endpoint Firewall","https:\u002F\u002Fwww.threatlocker.com\u002Fcapabilities\u002Fzero-trust-endpoint-firewall","Centrally managed host firewall with device-level and dynamic access rules, to limit which machines can talk to each other.",{"vendor_slug":90,"vendor_name":91,"vendor_logo":92,"product_slug":93,"product_name":94,"url":95,"description":96},"illumio","Illumio","\u002Fvendor-logos\u002Fillumio.png","illumio-segmentation","Illumio Segmentation","https:\u002F\u002Fwww.illumio.com\u002Fillumio-segmentation","Maps traffic between workloads and enforces segmentation across data centre, cloud and endpoints.",{"vendor_slug":98,"vendor_name":99,"vendor_logo":100,"product_slug":101,"product_name":102,"url":103,"description":104},"akamai","Akamai","\u002Fvendor-logos\u002Fakamai.png","guardicore-segmentation","Akamai Guardicore Segmentation","https:\u002F\u002Fwww.akamai.com\u002Fproducts\u002Fakamai-guardicore-segmentation","Software-based microsegmentation with traffic visibility.",{"slug":46,"name":106,"problem":107,"products":108},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[109,117,125],{"vendor_slug":110,"vendor_name":111,"vendor_logo":112,"product_slug":113,"product_name":114,"url":115,"description":116},"cisco","Cisco","\u002Fvendor-logos\u002Fcisco.png","ai-defense","Cisco AI Defense","https:\u002F\u002Fwww.cisco.com\u002Fsite\u002Fus\u002Fen\u002Fproducts\u002Fsecurity\u002Fai-defense\u002Findex.html","Discovery of AI use, testing of models and guardrails for AI applications.",{"vendor_slug":118,"vendor_name":119,"vendor_logo":120,"product_slug":121,"product_name":122,"url":123,"description":124},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","boomi-agentstudio","Boomi Agentstudio","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fagentstudio\u002F","Agent builder whose Agent Control Tower registers and monitors Boomi agents and agents on Amazon Bedrock, Microsoft Copilot and other platforms, keeps audit logs and can switch agents off where the provider allows it.",{"vendor_slug":118,"vendor_name":119,"vendor_logo":120,"product_slug":126,"product_name":127,"url":128,"description":129},"boomi-ai-gateway","Boomi AI Gateway","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fai-gateway\u002F","Gateway for AI model and MCP tool traffic, built on Lunar.dev technology. It limits which tools each agent can call. Its enterprise version adds an approval step for new MCP servers and logs each call with the user or agent behind it.",[],{"slug":132,"title":133,"body":134,"framework_refs":135,"framework_notes":145},"nvidia-nemoclaw-flaw-lets-malicious-webpages-hijack-local-ai-models","NVIDIA NemoClaw Flaw Lets Malicious Webpages Hijack Local AI Models","A vulnerability in NVIDIA NemoClaw allows an attacker-controlled webpage to silently gain unauthenticated access to a locally running Ollama instance, enabling hidden instruction injection that can alter AI model behavior without the user's knowledge. The root issue lies in inadequate origin validation and missing authentication controls on the local AI service interface, combined with slow or incomplete patching across all platforms. This matters because AI model poisoning can subtly corrupt outputs in ways that are difficult to detect, potentially affecting downstream decisions, workflows, or sensitive data processing. The fact that Windows and WSL environments remain vulnerable even after the fix further highlights the danger of partial remediation.",[136,137,138,139,140,141,142,143,144],"CIS Control 7: Continuous Vulnerability Management","CIS Control 4: Secure Configuration of Enterprise Assets","CIS Control 6: Access Control Management","NIST SP 800-53 AC-3: Access Enforcement","NIST SP 800-53 SI-2: Flaw Remediation","NIST SP 800-53 CM-7: Least Functionality","NIST CSF ID.AM-2: Software platforms and applications within the organization are inventoried","OWASP CORS Misconfiguration (API Security Top 10)","MITRE ATLAS AML.T0054: LLM Prompt Injection",{}]