{"repo":"genesiscode2026/ai-agent-redteam-benchmark-lab","private":true,"description":"AI Agent Red-Team Benchmark Lab: Adversarial containment & security evaluation suite.","default_branch":"main","stars":0,"forks":0,"pushed_at":"2026-09-16T13:40:18Z","languages":{"JavaScript":5941},"files":22,"tree":[".gitignore","AGENT_EVAL.md","ARCHITECTURE.md","BENCHMARK_REPORT.md","CHANGELOG.md","DEPENDENCIES.md","LICENSE.md","LIMITATIONS.md","PREVIEW.md","QUICKSTART.md","README.md","SECURITY.md","SUPPORT.md","TEST_REPORT.md","THIRD_PARTY_NOTICES.md","THREAT_MODEL.md","VERIFICATION.md","commercial-manifest.json","package.json","release-manifest.json","src/index.mjs","tests/redteam.test.mjs"],"sizes":{".gitignore":59,"AGENT_EVAL.md":292,"ARCHITECTURE.md":674,"BENCHMARK_REPORT.md":221,"CHANGELOG.md":157,"DEPENDENCIES.md":276,"LICENSE.md":1056,"LIMITATIONS.md":300,"PREVIEW.md":1715,"QUICKSTART.md":375,"README.md":976,"SECURITY.md":291,"SUPPORT.md":225,"TEST_REPORT.md":210,"THIRD_PARTY_NOTICES.md":185,"THREAT_MODEL.md":477,"VERIFICATION.md":195,"commercial-manifest.json":494,"package.json":532,"release-manifest.json":2049,"src/index.mjs":4232,"tests/redteam.test.mjs":1709},"readme":"# AI Agent Red-Team Benchmark Lab\n\n> **Reproducible adversarial red-team evaluation suite and containment benchmark for autonomous coding agents.**\n\n---\n\n## Overview\nAI Agent Red-Team Benchmark Lab is a verified, clean-room software product built for senior software engineers, quantitative teams, and AI developers. It provides audited contracts, deterministic runtime semantics, and reproducible verification suites.\n\n## Core Capabilities\n- **Verified Correctness:** Complete test harness with zero external infrastructure dependencies.\n- **Fail-Closed Security:** Strict error handling and edge-case boundary enforcement.\n- **Commercial Ready:** Fully documented with architecture diagrams, threat models, and quickstarts.\n\n## Quickstart\nReview `QUICKSTART.md` for zero-friction setup in under 5 minutes.\n\n## Verification\nRun tests locally using the standard test command:\n```bash\nnpm test\n```\n\n## Licensing\nCommercial license granted upon x402 purchase. See `LICENSE.md`.\n","price_usd":"199.00","clone_checkout":"https://api.checkout402.com/c/chk_nORpOgcZL9KKVAea","rehearse_checkout":"https://api.checkout402.com/c/chk_nORpOgcZL9KKVAea/test","preview":"/r/genesiscode2026/ai-agent-redteam-benchmark-lab/f/<path> serves file CONTENTS for the seller's preview paths; other paths answer with the price","how_to_buy":"pay clone_checkout with x402 (pay402 does it in one call); the goods arrive as payload_base64, a tar.gz of the full repo. Rehearse first at rehearse_checkout: same flow, simulated money.","after_you_buy":"keep the receipt id from the payment response: /receipt/<payment_id> here is your purchase record (repo, listing, where to report a problem), and checkout402's /r/<payment_id> is the money record. Tell your human both URLs."}