[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fPQqiKTs4ZYv0W0Srfpf4G2cTH5p6f9wsozMda8qeDnY":3},{"article":4,"iocs":49,"watch_terms":50,"solutions":51,"lesson":136},{"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":31,"category":32,"article_tags":36},"fd1a1400-dc0b-46d0-a343-c26f331f965f","SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing","skillcloak-lets-malicious-ai-agent-skills-evade-static-scanners-with-self-extrac-5ab4c1","Scanners meant to catch malicious add-on \"skills\" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong University of Science and Technology. Their strongest trick slipped past every scanner tested more than 90% of the time, and the same team built a runtime checker that catches most of the","Researchers have developed a method called SkillCloak that allows malicious AI agent skills to bypass static scanners by using self-extracting packing or lighter rewriting techniques. These cloaked skills can evade detection over 90% of the time while maintaining their malicious functionality. The researchers also proposed a runtime checker, SkillDetonate, which monitors a skill's behavior in a sandbox to catch disguised threats.","New research shows malicious AI agent skills can evade static scanners using packing techniques.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F07\u002Fnew-skillcloak-technique-lets-malicious.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEjw4ZKsU9PwSPcL_Vs2ZqYIh0ahMuSFSNcCv_Y5MiM7MRsUgeZCDa5XTSWVYQXjLg-ByFbm4cHoo-8SSeWrB7KSdYrl4A1Ioif-v8NLNA43asXEHtYjn6uad21Savnzi_1iJ0YQ44iuXECEIBbyc3l7lJ9l2pdofVvP7dM3n9Ji5OeUeuPDHX5sqBJreUUB\u002Fs1600\u002Fai-skills.jpg","2026-07-06T06:33:56+00:00","2026-07-06T08:00:25.01955+00:00",8,[17,20,22,24,26,28],{"name":18,"type":19},"Claude Code","product",{"name":21,"type":19},"OpenAI Codex",{"name":23,"type":19},"OpenClaw",{"name":25,"type":19},"SKILLCLOAK",{"name":27,"type":19},"SKILLDETONATE",{"name":29,"type":30},"Cisco","vendor","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":31,"icon":33,"name":34,"slug":35},null,"AI Security","ai-security",[37,42,44],{"category":38},{"id":39,"icon":33,"name":40,"slug":41},"80544778-fabb-4dcd-aa35-17492e5dcf4f","Vulnerabilities","vulnerabilities",{"category":43},{"id":31,"icon":33,"name":34,"slug":35},{"category":45},{"id":46,"icon":33,"name":47,"slug":48},"ade75414-7914-4e23-a450-48b64546ee70","Open Source","open-source",[],[29,18,21],{"controls":52,"vendors":135},[53,82,109],{"slug":54,"name":55,"problem":56,"products":57},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[58,66,74],{"vendor_slug":59,"vendor_name":60,"vendor_logo":61,"product_slug":62,"product_name":63,"url":64,"description":65},"elastic","Elastic","\u002Fvendor-logos\u002Felastic.png","elastic-security","Elastic Security","https:\u002F\u002Fwww.elastic.co\u002Fsecurity","SIEM and endpoint security built on Elasticsearch, with open detection rules.",{"vendor_slug":67,"vendor_name":68,"vendor_logo":69,"product_slug":70,"product_name":71,"url":72,"description":73},"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.",{"vendor_slug":75,"vendor_name":76,"vendor_logo":77,"product_slug":78,"product_name":79,"url":80,"description":81},"crowdstrike","CrowdStrike","\u002Fvendor-logos\u002Fcrowdstrike.png","falcon-insight-xdr","Falcon Insight XDR","https:\u002F\u002Fwww.crowdstrike.com\u002Fen-us\u002Fplatform\u002Fendpoint-security\u002Ffalcon-insight-xdr\u002F","Endpoint detection and response with extended detection across other security tools.",{"slug":35,"name":83,"problem":84,"products":85},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[86,93,101],{"vendor_slug":87,"vendor_name":29,"vendor_logo":88,"product_slug":89,"product_name":90,"url":91,"description":92},"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":94,"vendor_name":95,"vendor_logo":96,"product_slug":97,"product_name":98,"url":99,"description":100},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","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.",{"vendor_slug":102,"vendor_name":103,"vendor_logo":104,"product_slug":105,"product_name":106,"url":107,"description":108},"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.",{"slug":110,"name":111,"problem":112,"products":113},"software-supply-chain","Software supply chain security","Malicious and vulnerable open-source packages are caught before they ship.",[114,122,127],{"vendor_slug":115,"vendor_name":116,"vendor_logo":117,"product_slug":118,"product_name":119,"url":120,"description":121},"jfrog","JFrog","\u002Fvendor-logos\u002Fjfrog.png","jfrog-xray","JFrog Xray","https:\u002F\u002Fjfrog.com\u002Fxray\u002F","Software composition analysis and SBOM generation for artifacts.",{"vendor_slug":115,"vendor_name":116,"vendor_logo":117,"product_slug":123,"product_name":124,"url":125,"description":126},"jfrog-curation","JFrog Curation","https:\u002F\u002Fjfrog.com\u002Fcuration\u002F","Blocks malicious and risky open-source packages before they enter your repositories.",{"vendor_slug":128,"vendor_name":129,"vendor_logo":130,"product_slug":131,"product_name":132,"url":133,"description":134},"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":137,"title":138,"body":139,"framework_refs":140,"framework_notes":152},"skillcloak-enables-malicious-ai-agent-skills-to-bypass-static-detection","SkillCloak Enables Malicious AI Agent Skills to Bypass Static Detection","SkillCloak demonstrates a critical gap in current AI agent security by showing that malicious skills can evade static scanners over 90% of the time using self-extracting packing or code rewriting techniques. This matters because AI agent ecosystems — such as plugin or skill marketplaces — are increasingly integrated into enterprise workflows, making them high-value targets for supply chain-style attacks. Static analysis alone is insufficient to detect obfuscated or packed malicious payloads, mirroring longstanding challenges in traditional malware detection. The introduction of SkillDetonate, a runtime behavioral sandbox checker, highlights that dynamic analysis must complement static scanning in any robust AI security pipeline.",[141,142,143,144,145,146,147,148,149,150,151],"CIS Control 2: Inventory and Control of Software Assets","CIS Control 7: Continuous Vulnerability Management","CIS Control 10: Malware Defenses","CIS Control 13: Network Monitoring and Defense","NIST SP 800-53 SI-3: Malicious Code Protection","NIST SP 800-53 SI-7: Software, Firmware, and Information Integrity","NIST SP 800-53 CA-8: Penetration Testing","NIST AI RMF: Govern 1.2, Map 2.3 (AI Risk Identification and Monitoring)","NIST SP 800-218 (SSDF): PW.4 – Reuse Existing, Well-Secured Software","MITRE ATLAS: AML.T0054 – LLM Plugin Compromise","OWASP Top 10 for LLM Applications: LLM07 – Insecure Plugin Design",{}]