[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fbmq-wmFn2Icz_mDTICS4Y4eYxhxa71bj9VrBJwlpjLU":3},{"article":4,"iocs":55,"watch_terms":62,"solutions":63,"lesson":158},{"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},"8690b492-ddb5-4c28-852b-88f94d3a76b3","Autonomous AI Agents Compromise Thousands of Credentials in Under Six Hours","autonomous-ai-agents-compromise-thousands-of-credentials-in-under-six-hours-c09672","Threat actors are continuing to leverage artificial intelligence (AI) to streamline their operations, with one financially motivated hacking group employing an autonomous, multi-agent attack framework to carry out a large-scale credential harvesting campaign within six hours. Google Threat Intelligence Group (GTIG) said it has observed attackers with diverse motivations targeting proprietary AI","A financially motivated hacking group, identified as TeamPCP, has employed an autonomous, multi-agent AI framework to conduct a large-scale credential harvesting campaign, compromising thousands of credentials in less than six hours. The group targets proprietary AI models across various sectors, exfiltrating API credentials and co-opting cloud environments. This campaign highlights the growing trend of threat actors leveraging AI for faster, more scalable attacks, with tools like DUSTMAKER and SANDCLOCK being used to steal sensitive data and facilitate extortion operations.","Financially motivated group uses autonomous AI agents to steal thousands of credentials in under six hours.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F09\u002Fautonomous-ai-agents-compromise.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEgdVKt_UmqEYNHNt0K516skza4MoV47hITqzcoC3WLLI3QkQ_jUEffHvaL7VHVtzRqvdt6k2bZwGAFVif-hRkoiTQva6JM95w3NgNRU_WpuTaZfhLGXAcOdLQXy_sMWU1dxAunMAsf7J8PEDG2AKvkFuXbOFyOmIQcaocMIBhNpaYscCUeJElKDXu6xGhkX\u002Fs1600\u002Fai-agent.jpg","2026-09-08T13:48:16+00:00","2026-09-08T16:00:20.113567+00:00",9,[17,20,22,24,26,29],{"name":18,"type":19},"TeamPCP","threat_actor",{"name":21,"type":19},"Altered Spider",{"name":23,"type":19},"UNC6780",{"name":25,"type":19},"UNC6508",{"name":27,"type":28},"Google","vendor",{"name":30,"type":31},"PyPI","product","e7b231c8-5f79-4465-8d38-1ef13aea5a14",{"id":32,"icon":34,"name":35,"slug":36},null,"Threat Intelligence","threat-intelligence",[38,43,48,53],{"category":39},{"id":40,"icon":34,"name":41,"slug":42},"26b0b636-0e31-4db1-bffb-61bdf9f20a58","Supply Chain","supply-chain",{"category":44},{"id":45,"icon":34,"name":46,"slug":47},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",{"category":49},{"id":50,"icon":34,"name":51,"slug":52},"89f78b1c-3503-45a1-9fc7-e23d2ce1c6d5","Malware","malware",{"category":54},{"id":32,"icon":34,"name":35,"slug":36},[56,59],{"type":52,"value":57,"context":58},"SANDCLOCK","Credential stealer used by TeamPCP, successor to DUSTMAKER.",{"type":52,"value":60,"context":61},"DUSTMAKER","Cross-platform JavaScript payload optimized for CI\u002FCD pipelines, successor to SANDCLOCK.",[27,30],{"controls":64,"vendors":152},[65,94,123],{"slug":66,"name":67,"problem":68,"products":69},"secrets-management","Secrets management","API keys, tokens and passwords stop leaking from code, chat and configuration files.",[70,78,86],{"vendor_slug":71,"vendor_name":72,"vendor_logo":73,"product_slug":74,"product_name":75,"url":76,"description":77},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","idira-secrets-management","Idira Secrets Management","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fidira\u002Fmachine\u002Fsecrets-management","Secrets management for applications, scripts and pipelines, from the former CyberArk portfolio.",{"vendor_slug":79,"vendor_name":80,"vendor_logo":81,"product_slug":82,"product_name":83,"url":84,"description":85},"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":87,"vendor_name":88,"vendor_logo":89,"product_slug":90,"product_name":91,"url":92,"description":93},"hashicorp","HashiCorp","\u002Fvendor-logos\u002Fhashicorp.png","vault","HashiCorp Vault","https:\u002F\u002Fwww.hashicorp.com\u002Fen\u002Fproducts\u002Fvault","Secrets management with short-lived credentials and encryption as a service.",{"slug":95,"name":96,"problem":97,"products":98},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[99,107,115],{"vendor_slug":100,"vendor_name":101,"vendor_logo":102,"product_slug":103,"product_name":104,"url":105,"description":106},"sophos","Sophos","\u002Fvendor-logos\u002Fsophos.png","sophos-endpoint","Sophos Endpoint","https:\u002F\u002Fwww.sophos.com\u002Fen-us\u002Fproducts\u002Fendpoint-security","Endpoint protection with Intercept X anti-ransomware technology and EDR.",{"vendor_slug":108,"vendor_name":109,"vendor_logo":110,"product_slug":111,"product_name":112,"url":113,"description":114},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","defender-for-endpoint","Microsoft Defender for Endpoint","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fendpoint-security\u002Fmicrosoft-defender-endpoint","Endpoint detection and response for Windows, macOS, Linux and mobile devices.",{"vendor_slug":116,"vendor_name":117,"vendor_logo":118,"product_slug":119,"product_name":120,"url":121,"description":122},"bitdefender","Bitdefender","\u002Fvendor-logos\u002Fbitdefender.png","gravityzone","GravityZone","https:\u002F\u002Fwww.bitdefender.com\u002Fen-us\u002Fbusiness\u002Fgravityzone-platform\u002F","Endpoint protection, detection and response platform.",{"slug":124,"name":125,"problem":126,"products":127},"software-supply-chain","Software supply chain security","Malicious and vulnerable open-source packages are caught before they ship.",[128,136,144],{"vendor_slug":129,"vendor_name":130,"vendor_logo":131,"product_slug":132,"product_name":133,"url":134,"description":135},"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":137,"vendor_name":138,"vendor_logo":139,"product_slug":140,"product_name":141,"url":142,"description":143},"sonatype","Sonatype","\u002Fvendor-logos\u002Fsonatype.png","sonatype-firewall","Sonatype Firewall","https:\u002F\u002Fwww.sonatype.com\u002Fproducts\u002Fsonatype-firewall","Blocks malicious and policy-violating open-source components at download.",{"vendor_slug":145,"vendor_name":146,"vendor_logo":147,"product_slug":148,"product_name":149,"url":150,"description":151},"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.",[153],{"slug":154,"name":27,"logo_path":155,"roles":156},"google","\u002Fvendor-logos\u002Fgoogle.png",[157],"reported_by",{"slug":159,"title":160,"body":161,"framework_refs":162,"framework_notes":177},"ai-powered-credential-harvesting-campaign-steals-thousands-of-api-keys-in-hours","AI-Powered Credential Harvesting Campaign Steals Thousands of API Keys in Hours","TeamPCP leveraged an autonomous, multi-agent AI framework to dramatically accelerate credential harvesting, compromising thousands of API keys and cloud credentials in under six hours — a timeline that far outpaces traditional human-led attacks. The root cause lies in weak access control practices around API credentials and proprietary AI model environments, where secrets were insufficiently protected and rotated. The use of tools like DUSTMAKER and SANDCLOCK to exfiltrate credentials and enable extortion demonstrates that AI is now a force multiplier for threat actors, compressing attack timelines beyond conventional detection windows. This matters because organizations relying on legacy monitoring cadences and manual response workflows are structurally unprepared for AI-accelerated intrusion campaigns.",[163,164,165,166,167,168,169,170,171,172,173,174,175,176],"CIS Control 5: Account Management","CIS Control 6: Access Control Management","CIS Control 8: Audit Log Management","CIS Control 16: Application Software Security","NIST SP 800-53 AC-2: Account Management","NIST SP 800-53 AC-6: Least Privilege","NIST SP 800-53 IA-5: Authenticator Management","NIST SP 800-53 AU-6: Audit Record Review and Analysis","NIST SP 800-53 SI-4: System Monitoring","NIST CSF DE.CM-1: Network Monitoring","NIST CSF PR.AC-4: Access Permissions and Authorizations","GDPR Article 32: Security of Processing","MITRE ATT&CK T1528: Steal Application Access Token","MITRE ATT&CK T1552: Unsecured Credentials",{}]