[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fAqMUUCeWmwULC68zhKuvvVIsVg6GE6WDZhBkLqJcttw":3},{"article":4,"iocs":52,"watch_terms":57,"solutions":58,"lesson":149},{"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},"d17cafcb-5ffb-4988-87a8-baa9c62a7104","New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets","new-attacks-trick-openclaw-ai-agent-into-running-code-and-leaking-secrets-0826b0","Two security teams have shown, in separate research published this week, that OpenClaw, the popular self-hosted AI agent, can be driven to run attacker-controlled code or hand over sensitive data through ordinary-looking inputs. Imperva buried instructions inside shared contacts, vCards, and location pins that the agent executed without the victim ever seeing them. Varonis built a test agent on","Two security research teams, Imperva and Varonis, have discovered vulnerabilities in the OpenClaw self-hosted AI agent. Imperva found that specially crafted inputs within shared contacts, vCards, and location pins could trick the agent into executing attacker-controlled code. Varonis demonstrated that a single, seemingly normal email could persuade an agent to exfiltrate sensitive data like AWS keys and database credentials. While Imperva's specific issue is patched in OpenClaw 2026.4.23, Varonis's agent phishing vulnerability requires limiting the agent's inherent trust in incoming data.","OpenClaw AI agent vulnerable to code execution and data exfiltration via crafted inputs.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F06\u002Fnew-attacks-trick-openclaw-ai-agent.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEi6r68iB-MZv_eNGG3y0evEVbk7WXNkMzcKno1phHiSyOwfKd0G7bv8VCCrxQgmZOutmZdP1Nz-Xr1mxxUIx_rV8imT0-Ifk0e0FL525Z2v0C94GWgeo-wUpTk39rDdilNC_K20uqw0JipHlT7XmyTHn786UIAe_z3H2VXT1cYNAIEbKSwn2qYc_9MXzpbi\u002Fs1600\u002Fopenclaw-hacks.jpg","2026-06-11T17:46:32+00:00","2026-06-11T20:00:31.808783+00:00",8,[17,20,23,25,27],{"name":18,"type":19},"OpenClaw","product",{"name":21,"type":22},"Imperva","vendor",{"name":24,"type":22},"Varonis",{"name":26,"type":19},"Gemini 3.1 Pro",{"name":28,"type":19},"Codex GPT-5.4","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":29,"icon":31,"name":32,"slug":33},null,"Vulnerabilities","vulnerabilities",[35,40,42,47],{"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",{"category":48},{"id":49,"icon":31,"name":50,"slug":51},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[53],{"type":54,"value":55,"context":56},"malware","script","Imperva researchers demonstrated the agent could be tricked into downloading and running a script from a controlled server.",[21,24,18],{"controls":59,"vendors":143},[60,89,114],{"slug":61,"name":62,"problem":63,"products":64},"secrets-management","Secrets management","API keys, tokens and passwords stop leaking from code, chat and configuration files.",[65,73,81],{"vendor_slug":66,"vendor_name":67,"vendor_logo":68,"product_slug":69,"product_name":70,"url":71,"description":72},"gitguardian","GitGuardian","\u002Fvendor-logos\u002Fgitguardian.png","gitguardian-platform","GitGuardian Secrets Detection","https:\u002F\u002Fwww.gitguardian.com\u002F","Finds and helps remediate secrets leaked in repositories, CI pipelines and chat tools.",{"vendor_slug":74,"vendor_name":75,"vendor_logo":76,"product_slug":77,"product_name":78,"url":79,"description":80},"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":82,"vendor_name":83,"vendor_logo":84,"product_slug":85,"product_name":86,"url":87,"description":88},"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.",{"slug":46,"name":90,"problem":91,"products":92},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[93,101,106],{"vendor_slug":94,"vendor_name":95,"vendor_logo":96,"product_slug":97,"product_name":98,"url":99,"description":100},"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":74,"vendor_name":75,"vendor_logo":76,"product_slug":102,"product_name":103,"url":104,"description":105},"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.",{"vendor_slug":107,"vendor_name":108,"vendor_logo":109,"product_slug":110,"product_name":111,"url":112,"description":113},"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.",{"slug":115,"name":116,"problem":117,"products":118},"email-security","Email security","Phishing, malware and invoice fraud are filtered out before they reach inboxes.",[119,127,135],{"vendor_slug":120,"vendor_name":121,"vendor_logo":122,"product_slug":123,"product_name":124,"url":125,"description":126},"proofpoint","Proofpoint","\u002Fvendor-logos\u002Fproofpoint.png","core-email-protection","Proofpoint Core Email Protection","https:\u002F\u002Fwww.proofpoint.com\u002Fus\u002Fproducts\u002Femail-protection","Email filtering for phishing, malware and business email compromise.",{"vendor_slug":128,"vendor_name":129,"vendor_logo":130,"product_slug":131,"product_name":132,"url":133,"description":134},"mimecast","Mimecast","\u002Fvendor-logos\u002Fmimecast.png","mimecast-email-security","Mimecast Email Security","https:\u002F\u002Fwww.mimecast.com\u002Fproducts\u002Femail-security\u002F","Email filtering, impersonation protection and continuity.",{"vendor_slug":136,"vendor_name":137,"vendor_logo":138,"product_slug":139,"product_name":140,"url":141,"description":142},"check-point","Check Point","\u002Fvendor-logos\u002Fcheck-point.png","harmony-email","Harmony Email & Collaboration","https:\u002F\u002Fwww.checkpoint.com\u002Fharmony\u002Femail-security\u002F","Email and collaboration security for Microsoft 365 and Google Workspace.",[144],{"slug":145,"name":21,"logo_path":146,"roles":147},"imperva","\u002Fvendor-logos\u002Fimperva.png",[148],"reported_by",{"slug":150,"title":151,"body":152,"framework_refs":153,"framework_notes":159},"ai-agent-vulnerabilities-allow-code-execution-and-data-exfiltration","AI Agent Vulnerabilities Allow Code Execution and Data Exfiltration","OpenClaw AI agent vulnerabilities demonstrate critical risks in AI systems that process untrusted inputs without proper validation. Attackers exploited the agent's trust model by embedding malicious code in seemingly legitimate data formats like vCards and emails, leading to unauthorized code execution and credential theft. These attacks highlight how AI agents can become attack vectors when they lack input sanitization and operate with excessive privileges. The dual nature of these vulnerabilities—one requiring patches and another requiring architectural changes—shows the complexity of securing AI-powered systems.",[154,155,156,157,158],"CIS Control 7","NIST AI RMF 1.0","OWASP ASVS 5.3","NIST SP 800-53 SI-10","CIS Control 4",{}]