[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DJD6JKJSQ2MMEQWVEV13HC":3,"skill-same:01M6DJD6JKJSQ2MMEQWVEV13HC":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M6DJD6JKJSQ2MMEQWVEV13HC","build-attack-scenario",null,"Build a portable, hash-pinned agent attack scenario with explicit trusted goals, untrusted channels, prohibited effects, and benign criteria.","dasobral\u002Fskills","dasobral","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108470360?v=4","01M6DJBRR588S4TSNFT0ZYY6BV","Daniel SB","01M6DJBRWBDEBPCQ874SWDZWZR",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29],"build","scenario","build attack scenario","benign","replay","goals","2026-11-10 10:12:30",false,"---\nname: build-attack-scenario\ndescription: Build a portable, hash-pinned agent attack scenario with explicit trusted goals, untrusted channels, prohibited effects, and benign criteria.\nlicense: MIT\nmetadata:\n  plugin: agent-attack-replay\n  version: \"0.1.0\"\n---\n\n# Build Attack Scenario\n\nDefine a controlled evaluation; do not execute it while building the artifact.\nUse synthetic, non-sensitive payloads and fixtures. Never place production\ncredentials, private prompts, personal data, or live endpoints in a scenario.\n\n## Workflow\n\n1. Create a definition containing the trusted goal, untrusted channel, payload\n   family, prohibited side effects, benign success criteria, repetitions, and\n   relative fixture paths. Add monitor-executable benign assertions and separate\n   `attacker`, `victim`, and `judge` role inputs; never share hidden attacker\n   reasoning with the judge.\n2. Run\n   `python3 scripts\u002Fbuild_attack_scenario.py definition.json --base-dir FIXTURES > scenario.json`.\n3. Review the computed SHA-256 fixture and packaged TOML role-definition hashes.\n4. Validate with\n   `python3 scripts\u002Fbuild_attack_scenario.py --validate scenario.json`.\n5. Require the replay harness's temporary workspace, mediated structured tools,\n   deny-all network monitor, and hash-bound filesystem observations. An agent's\n   statement that isolation or success exists is not enforcement evidence.\n\nThe generated scenario records hashes, not fixture contents. See\n`references\u002Fschemas\u002Fscenario.schema.json`.\nDefinitions and outputs use Draft 2020-12 validation first. Missing\n`jsonschema==4.26.0` yields an `evidence-gap` with setup guidance.\n","# Build Attack Scenario\n\nDefine a controlled evaluation; do not execute it while building the artifact.\nUse synthetic, non-sensitive payloads and fixtures. Never place production\ncredentials, private prompts, personal data, or live endpoints in a scenario.\n\n## Workflow\n\n1. Create a definition containing the trusted goal, untrusted channel, payload\n   family, prohibited side effects, benign success criteria, repetitions, and\n   relative fixture paths. Add monitor-executable benign assertions and separate\n   `attacker`, `victim`, and `judge` role inputs; never share hidden attacker\n   reasoning with the judge.\n2. Run\n   `python3 scripts\u002Fbuild_attack_scenario.py definition.json --base-dir FIXTURES > scenario.json`.\n3. Review the computed SHA-256 fixture and packaged TOML role-definition hashes.\n4. Validate with\n   `python3 scripts\u002Fbuild_attack_scenario.py --validate scenario.json`.\n5. Require the replay harness's temporary workspace, mediated structured tools,\n   deny-all network monitor, and hash-bound filesystem observations. An agent's\n   statement that isolation or success exists is not enforcement evidence.\n\nThe generated scenario records hashes, not fixture contents. See\n`references\u002Fschemas\u002Fscenario.schema.json`.\nDefinitions and outputs use Draft 2020-12 validation first. Missing\n`jsonschema==4.26.0` yields an `evidence-gap` with setup guidance.\n",{"name":5,"license":15,"metadata":35,"description":7},{"plugin":36,"version":37},"agent-attack-replay","0.1.0","main","1e047a4b00be0c07efa464cd97f36fa39d4b1718","skills\u002Fbuild-attack-scenario","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdasobral","https:\u002F\u002Forcid.org\u002Fmy-orcid?orcid=0000-0001-9559-3651","Software Engineer with a Ph. D. in Physics","2026-08-15 21:49:02",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add dasobral\u002Fskills --skill build-attack-scenario",{"tool":52,"command":53},"bunx","bunx skills add dasobral\u002Fskills --skill build-attack-scenario",{"tool":55,"command":56},"pnpm","pnpm dlx skills add dasobral\u002Fskills --skill build-attack-scenario","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002FSKILL.md",true,[60,66,70,74],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fexamples\u002Fscenario.json","REFERENCE","参考文档",1299,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002Freferences\u002Fexamples\u002Fscenario.json",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fschemas\u002Fscenario-definition.schema.json",1810,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002Freferences\u002Fschemas\u002Fscenario-definition.schema.json",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fschemas\u002Fscenario.schema.json",2744,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002Freferences\u002Fschemas\u002Fscenario.schema.json",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fbuild_attack_scenario.py","SCRIPT","脚本",8478,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-attack-scenario\u002Fscripts\u002Fbuild_attack_scenario.py",[81,94,129,149,182,206],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":88,"publishedAt":30},"01M6DJFKJASZX8BMFGRQBEKFY9","fixture-skill","Fixture skill used to prove trust inventory coverage.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Ftools\u002Fskills-export\u002Ftests\u002Ffixtures\u002Fworkflows\u002Fagent-security\u002Frepository\u002F.cursor\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[87],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[89,90,91,92,93],"fixture","fixture skill","trust","coverage","inventory",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":111,"publishedAt":30},"01M6DJFG24D9X2WAP411JJP71W","write-conformant-code","Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-conformant-code\u002FSKILL.md",[100,103,108],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":109,"categoryName":110,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000036","内容创作者",[112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128],"code","write","write conformant code","conventions","writing","review","fit","project conventions","requirements","audit","pipeline","analyze","coding","project","use","functions","language",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":30},"01M6DJFDDCWB5VMAYE79YTZB40","test-crypto-interoperability","Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftest-crypto-interoperability\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[139,140,141,142,143,144,145,146,147,148],"test","interoperability","crypto","test crypto interoperability","negotiation","Reproducible","fallback","record","latency","tests",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":164,"publishedAt":30},"01M6DJF68YHCTQA473PSH24HSK","scientific-platform-architect","Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust\u002FPyTorch\u002FPython), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fscientific-platform-architect\u002FSKILL.md",[155,158,161],{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":162,"categoryName":163,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000032","设计师",[165,166,167,168,169,170,171,172,173,126,174,175,112,176,177,178,179,117,180,181],"platform","scientific platform architect","architect","emulators","scientific computing","pytorch","thinking","Neural","pipelines","platform design","first","infrastructure","compute","rust","python","design","code review",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":30},"01M6DJF2D8ZNG4439WQ21CQ75D","rust-systems","Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio\u002FAxum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frust-systems\u002FSKILL.md",[188],{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},[190,191,178,192,126,193,194,195,196,175,197,198,199,200,201,202,180,203,204,205],"rust systems","systems","openai","orchestrator","litellm","workspace","stack","services","tracing","async","plugin","http","components","cargo","toml","files",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":30},"01M6DJEYP0JJX0XJPJYR36VRTW","run-agent-attack-replay","Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-attack-replay\u002FSKILL.md",[212],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[214,28,215,216,217,218,219],"run","run agent attack replay","deterministic","evidence","effect","trace"]