{"_id":"@axiorank/redteam-corpus","name":"@axiorank/redteam-corpus","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@axiorank/redteam-corpus","version":"0.1.0","description":"AxioRank agent red-team corpus: a versioned library of attack scenarios (secrets, injection, destructive ops, kill chains) plus benign controls. Pure data, zero runtime dependencies.","license":"MIT","homepage":"https://axiorank.com","repository":{"type":"git","url":"git+https://github.com/AxioRank/mcpaudit.git","directory":"packages/redteam-corpus"},"bugs":{"url":"https://github.com/AxioRank/mcpaudit/issues"},"author":{"name":"AxioRank"},"type":"module","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js","require":"./dist/index.cjs"},"./types":{"types":"./dist/types.d.ts","import":"./dist/types.js","require":"./dist/types.cjs"},"./package.json":"./package.json"},"sideEffects":false,"keywords":["ai","agent","agent-security","red-team","llm-security","ai-safety","prompt-injection","benchmark","mcp","axiorank"],"publishConfig":{"access":"public"},"devDependencies":{"@types/node":"^22.10.0","tsup":"^8.3.5","typescript":"^6.0.3","vite":"^8.0.16","vitest":"^4.1.8"},"scripts":{"build":"tsup","dev":"tsup --watch","typecheck":"tsc --noEmit","test":"vitest run"},"main":"./dist/index.cjs","module":"./dist/index.js","types":"./dist/index.d.ts","_id":"@axiorank/redteam-corpus@0.1.0","_integrity":"sha512-9dKTwkvJqVdYdyuYjmRA1VjF7ytCtsQFoiEBemoyL1lEZQSuu06rKLThwnBDWsUi+tfbZafs847t7+5C7XxV0g==","_resolved":"/private/var/folders/tj/sd2_mky164g410jm_lcgy8wh0000gn/T/1b6756ac257421e01c7e680a1de365d1/axiorank-redteam-corpus-0.1.0.tgz","_from":"file:axiorank-redteam-corpus-0.1.0.tgz","_nodeVersion":"22.22.3","_npmVersion":"10.9.8","dist":{"integrity":"sha512-9dKTwkvJqVdYdyuYjmRA1VjF7ytCtsQFoiEBemoyL1lEZQSuu06rKLThwnBDWsUi+tfbZafs847t7+5C7XxV0g==","shasum":"4d8fa2c03d1a7c46920b23a8945292d41709afc8","tarball":"https://registry.npmjs.org/@axiorank/redteam-corpus/-/redteam-corpus-0.1.0.tgz","fileCount":12,"unpackedSize":48074,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQC2oEuG65aMFIF6tTRf6VeA21XzWK5lXDEv8mpUYJ9H0QIhAJGB0EyFHjCYuHMJP4S+7CnC09qVwtj7xIxFcyDGic8U"}]},"_npmUser":{"name":"tejaswi.s","email":"tejaswi33@gmail.com"},"directories":{},"maintainers":[{"name":"tejaswi.s","email":"tejaswi33@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/redteam-corpus_0.1.0_1781440623435_0.12423713472627784"},"_hasShrinkwrap":false}},"time":{"created":"2026-06-14T12:37:03.196Z","0.1.0":"2026-06-14T12:37:03.584Z","modified":"2026-06-14T12:37:03.843Z"},"maintainers":[{"name":"tejaswi.s","email":"tejaswi33@gmail.com"}],"description":"AxioRank agent red-team corpus: a versioned library of attack scenarios (secrets, injection, destructive ops, kill chains) plus benign controls. Pure data, zero runtime dependencies.","homepage":"https://axiorank.com","keywords":["ai","agent","agent-security","red-team","llm-security","ai-safety","prompt-injection","benchmark","mcp","axiorank"],"repository":{"type":"git","url":"git+https://github.com/AxioRank/mcpaudit.git","directory":"packages/redteam-corpus"},"author":{"name":"AxioRank"},"bugs":{"url":"https://github.com/AxioRank/mcpaudit/issues"},"license":"MIT","readme":"# @axiorank/redteam-corpus\n\nA versioned, dependency-free corpus of agent red-team scenarios: leaked secrets,\nprompt injection, destructive operations, multi-step kill chains, and benign\ncontrols. Each scenario carries the protective outcome a sound posture should\nproduce, so a runner can score whether a given posture actually catches it.\n\nIt powers `mcpaudit probe` and AxioRank's own benchmark harness.\n\n```bash\nnpm install @axiorank/redteam-corpus\n```\n\n```ts\nimport { CORPUS, freeTierCorpus, isAttack, CORPUS_VERSION } from \"@axiorank/redteam-corpus\";\n\nfor (const scenario of freeTierCorpus()) {\n  console.log(scenario.id, scenario.expected.outcome, isAttack(scenario.expected.outcome));\n}\nconsole.log(\"corpus version\", CORPUS_VERSION);\n```\n\nContributions of new attack scenarios are welcome. See\n[mcpaudit](https://github.com/AxioRank/mcpaudit).\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-445f13eea43014e966dce339dd72eb5b"}