{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"agent-security-red-teaming","title":"Insights into AI Agent Security from a Large-Scale Red-Teaming Competition | NIST","aliases":[],"authors":[],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"technical-report","sourceId":"agent-security-red-teaming-publication","attributionSourceId":"agent-security-red-teaming-publication","originalUrl":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition","publicationDate":"2026-03-23","updatedOn":"2026-10-25","areas":["cybersecurity"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"nist","role":"publisher","sourceId":"agent-security-red-teaming-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Analyzes findings from an agent red-teaming competition to characterize attacks and evaluation limitations.","zh":"分析智能体红队竞赛中的发现，刻画攻击方式和评测局限。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":["evaluation-audit"]},"reading":{"id":"agent-security-red-teaming","title":"Insights into AI Agent Security from a Large-Scale Red-Teaming Competition | NIST","en":{"question":"What does a public adversarial competition reveal about agent hijacking?","design":"CAISI and partners analyze competition attacks and post-competition transfer across models and scenarios, rather than only fixed automated templates.","findings":["Some attack families transferred across models and scenarios.","Attacks successful against more robust models tended to transfer to weaker models more than the reverse."],"interpretation":"NUWA interpretation: adaptive human red teaming exposes shared instruction-boundary failures.","limits":"The official blog is a research summary, not a complete competition protocol or a deployment-frequency estimate.","decisionRelevance":"Model recommendation: use the competition as complementary evidence and recover the paper’s sampling and transfer denominators before quantification.","takeaway":"NUWA interpretation: adaptive human red teaming exposes shared instruction-boundary failures.","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"Model recommendation: use the competition as complementary evidence and recover the paper’s sampling and transfer denominators before quantification."},"zh":{"question":"公开对抗竞赛能揭示哪些智能体劫持问题？","design":"CAISI与伙伴分析竞赛攻击及赛后跨模型、跨场景迁移，而非仅固定自动模板。","findings":["部分攻击族可跨模型与场景迁移。","对较稳健模型有效的攻击更易迁移至弱模型，反向较少。"],"interpretation":"NUWA 解读：自适应人工红队揭示共享指令边界问题。","limits":"官网博客只是研究概述，不是完整竞赛协议或部署发生频率。","decisionRelevance":"模型建议：作互补证据，量化前取得论文抽样和迁移分母。","takeaway":"NUWA 解读：自适应人工红队揭示共享指令边界问题。","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"模型建议：作互补证据，量化前取得论文抽样和迁移分母。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"agent-security-red-teaming-publication","url":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition","locator":"Background","version":"Selected original resource https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition; sha256:81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd; archived source capture; exact capture time not independently established","artifactSha256":"81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd"},{"sourceId":"agent-security-red-teaming-publication","url":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition","locator":"Key Findings","version":"Selected original resource https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition; sha256:81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd; archived source capture; exact capture time not independently established","artifactSha256":"81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd"},{"sourceId":"agent-security-red-teaming-publication","url":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition","locator":"Takeaways","version":"Selected original resource https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition; sha256:81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd; archived source capture; exact capture time not independently established","artifactSha256":"81546d5b664cf475535269d3dc95732d5ccaffa8730021a628898a74c8391abd"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"a32e0eb798ddf854b5991a352dba0b1e5b4988c9f987cad81042c58cc4ce626f"}},"sources":[{"id":"agent-security-red-teaming-publication","title":"Insights into AI Agent Security from a Large-Scale Red-Teaming Competition","url":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition","version":"Source capture 2026-10-25","publicationDate":"2026-03-23","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://www.nist.gov/blogs/caisi-research-blog/insights-ai-agent-security-large-scale-red-teaming-competition"}]}