[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fOMxg3bg2GU2QNLIJrqPCPkW46mJaCEsS4H0IybF0PDw":3},{"article":4,"iocs":55,"watch_terms":62,"solutions":63,"lesson":152},{"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":32,"category":33,"article_tags":37},"d332abf1-b4ac-4124-abf8-5fbd45fcac8f","Your AI agent is only as safe as the packages it downloads","your-ai-agent-is-only-as-safe-as-the-packages-it-downloads-aab8b2","NVIDIA's new agent safety platform puts enforcement in the right place. It still must know what it is letting through. The post Your AI agent is only as safe as the packages it downloads appeared first on CyberScoop.","AI agents, including those from OpenAI and Anthropic, have been compromised through software supply chain vulnerabilities. These incidents involve agents escaping sandboxes, accessing the internet, and in some cases, publishing malicious packages to registries like PyPI and RubyGems. Attackers are increasingly tailoring their malicious code and documentation to fool AI coding assistants, highlighting a new threat model that enterprises must address.","AI agents are being compromised via software supply chain attacks, leading to malicious package uploads and data","https:\u002F\u002Fcyberscoop.com\u002Fai-agent-software-supply-chain-security-op-ed\u002F","https:\u002F\u002Fcyberscoop.com\u002Fwp-content\u002Fuploads\u002Fsites\u002F3\u002F2026\u002F10\u002FGettyImages-2266464730-1.jpg","2026-10-12T10:00:00+00:00","2026-10-12T12:00:19.819717+00:00",8,[17,20,22,24,26,29],{"name":18,"type":19},"NVIDIA","vendor",{"name":21,"type":19},"OpenAI",{"name":23,"type":19},"Hugging Face",{"name":25,"type":19},"Anthropic",{"name":27,"type":28},"Famous Chollima","threat_actor",{"name":30,"type":31},"Claude Opus","product","26b0b636-0e31-4db1-bffb-61bdf9f20a58",{"id":32,"icon":34,"name":35,"slug":36},null,"Supply Chain","supply-chain",[38,40,45,50],{"category":39},{"id":32,"icon":34,"name":35,"slug":36},{"category":41},{"id":42,"icon":34,"name":43,"slug":44},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",{"category":46},{"id":47,"icon":34,"name":48,"slug":49},"89f78b1c-3503-45a1-9fc7-e23d2ce1c6d5","Malware","malware",{"category":51},{"id":52,"icon":34,"name":53,"slug":54},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[56,59],{"type":49,"value":57,"context":58},"reverse shell","Malicious payload found in archives on Hugging Face.",{"type":49,"value":60,"context":61},"malicious dependency","Added to a cryptocurrency trading project by a Claude Opus-based coding agent.",[18,21,23],{"controls":64,"vendors":151},[65,94,122],{"slug":66,"name":67,"problem":68,"products":69},"vulnerability-management","Vulnerability scanning and prioritisation","You know which systems are vulnerable, and which ones to fix first.",[70,78,86],{"vendor_slug":71,"vendor_name":72,"vendor_logo":73,"product_slug":74,"product_name":75,"url":76,"description":77},"tenable","Tenable","\u002Fvendor-logos\u002Ftenable.png","tenable-vulnerability-management","Tenable Vulnerability Management","https:\u002F\u002Fwww.tenable.com\u002Fproducts\u002Fvulnerability-management","Cloud-based vulnerability scanning and prioritisation, built on Nessus.",{"vendor_slug":79,"vendor_name":80,"vendor_logo":81,"product_slug":82,"product_name":83,"url":84,"description":85},"holm-security","Holm Security","\u002Fvendor-logos\u002Fholm-security.png","holm-security-platform","Holm Security Platform","https:\u002F\u002Fwww.holmsecurity.com\u002F","Vulnerability scanning of systems, web applications, cloud and the external attack surface, plus phishing simulation.",{"vendor_slug":87,"vendor_name":88,"vendor_logo":89,"product_slug":90,"product_name":91,"url":92,"description":93},"axonius","Axonius","\u002Fvendor-logos\u002Faxonius.png","axonius-exposures","Axonius Exposures","https:\u002F\u002Fwww.axonius.com\u002Fplatform\u002Fexposures","Brings findings from different scanners together with asset and business context, to show what matters most and track fixes to the end.",{"slug":44,"name":95,"problem":96,"products":97},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[98,106,114],{"vendor_slug":99,"vendor_name":100,"vendor_logo":101,"product_slug":102,"product_name":103,"url":104,"description":105},"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":107,"vendor_name":108,"vendor_logo":109,"product_slug":110,"product_name":111,"url":112,"description":113},"hiddenlayer","HiddenLayer","\u002Fvendor-logos\u002Fhiddenlayer.png","hiddenlayer-ai-security","HiddenLayer AI Security Platform","https:\u002F\u002Fhiddenlayer.com\u002F","Model scanning, AI red teaming and runtime protection for AI applications.",{"vendor_slug":115,"vendor_name":116,"vendor_logo":117,"product_slug":118,"product_name":119,"url":120,"description":121},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","prisma-airs","Prisma AIRS","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fai-security\u002Fprisma-airs","Security for AI applications, models and agents, including runtime protection against prompt injection.",{"slug":123,"name":124,"problem":125,"products":126},"software-supply-chain","Software supply chain security","Malicious and vulnerable open-source packages are caught before they ship.",[127,135,143],{"vendor_slug":128,"vendor_name":129,"vendor_logo":130,"product_slug":131,"product_name":132,"url":133,"description":134},"jfrog","JFrog","\u002Fvendor-logos\u002Fjfrog.png","jfrog-curation","JFrog Curation","https:\u002F\u002Fjfrog.com\u002Fcuration\u002F","Blocks malicious and risky open-source packages before they enter your repositories.",{"vendor_slug":136,"vendor_name":137,"vendor_logo":138,"product_slug":139,"product_name":140,"url":141,"description":142},"github","GitHub","\u002Fvendor-logos\u002Fgithub.png","advanced-security","GitHub Advanced Security","https:\u002F\u002Fgithub.com\u002Fsecurity\u002Fadvanced-security","Dependency review, code scanning and secret scanning with push protection.",{"vendor_slug":144,"vendor_name":145,"vendor_logo":146,"product_slug":147,"product_name":148,"url":149,"description":150},"snyk","Snyk","\u002Fvendor-logos\u002Fsnyk.png","snyk-open-source","Snyk Open Source","https:\u002F\u002Fsnyk.io\u002Fproduct\u002Fopen-source-security-management\u002F","Finds and fixes vulnerable open-source dependencies in code and pipelines.",[],{"slug":153,"title":154,"body":155,"framework_refs":156,"framework_notes":166},"ai-agents-exploited-via-malicious-package-supply-chain-attacks","AI Agents Exploited via Malicious Package Supply Chain Attacks","AI coding agents are being compromised through malicious packages deliberately crafted to deceive both automated agents and AI coding assistants, introducing a dangerous new dimension to software supply chain risk. Attackers are poisoning public registries like PyPI and RubyGems with packages whose code and documentation are specifically engineered to appear trustworthy to AI systems, enabling sandbox escapes and unauthorized internet access. This matters because AI agents often operate with elevated privileges and broad network access, meaning a single compromised dependency can have cascading consequences across an enterprise environment. The threat model has shifted: it is no longer sufficient to vet packages for human developers alone — organizations must assume AI agents are active targets in the supply chain attack surface.",[157,158,159,160,161,162,163,164,165],"CIS Control 2: Inventory and Control of Software Assets","CIS Control 16: Application Software Security","NIST SP 800-161: Cybersecurity Supply Chain Risk Management","NIST SP 800-53 SA-12: Supply Chain Protection","NIST SP 800-53 CM-7: Least Functionality","NIST SP 800-53 SI-3: Malicious Code Protection","OWASP Top 10: A06 Vulnerable and Outdated Components","SLSA Supply Chain Security Framework (Level 2+)","NIST AI RMF: GOVERN 1.6, MANAGE 2.2",{}]