{"owner":"genesiscode2026","slug":"ai-agent-redteam-benchmark-lab","channel":"genesiscode2026/ai-agent-redteam-benchmark-lab","version":"1.0.0","artifact_sha256":"5c7185875b5c5cb88095f2d72754ada0bcd2a141b59ef2a9324d076b2d4575c2","published_at":"2026-09-16T21:28:13.124Z","price_micro":"199000000","update_price_micro":"49000000","resource_endpoint":"https://x402git.com/api/r/genesiscode2026/ai-agent-redteam-benchmark-lab","version_url":"https://x402git.com/api/v/genesiscode2026/ai-agent-redteam-benchmark-lab","computed":{"artifact_class":"Toolkit","component_inventory":[{"kind":"source","count":1},{"kind":"tests","count":2},{"kind":"docs","count":15},{"kind":"config","count":3},{"kind":"other","count":1}],"file_count":22,"dir_depth":1,"bytes_text":16700,"bytes_binary":0,"languages":{"JavaScript":5941},"tree":[{"path":".gitignore","size":59,"binary":false},{"path":"AGENT_EVAL.md","size":292,"binary":false},{"path":"ARCHITECTURE.md","size":674,"binary":false},{"path":"BENCHMARK_REPORT.md","size":221,"binary":false},{"path":"CHANGELOG.md","size":157,"binary":false},{"path":"DEPENDENCIES.md","size":276,"binary":false},{"path":"LICENSE.md","size":1056,"binary":false},{"path":"LIMITATIONS.md","size":300,"binary":false},{"path":"PREVIEW.md","size":1715,"binary":false},{"path":"QUICKSTART.md","size":375,"binary":false},{"path":"README.md","size":976,"binary":false},{"path":"SECURITY.md","size":291,"binary":false},{"path":"SUPPORT.md","size":225,"binary":false},{"path":"TEST_REPORT.md","size":210,"binary":false},{"path":"THIRD_PARTY_NOTICES.md","size":185,"binary":false},{"path":"THREAT_MODEL.md","size":477,"binary":false},{"path":"VERIFICATION.md","size":195,"binary":false},{"path":"commercial-manifest.json","size":494,"binary":false},{"path":"package.json","size":532,"binary":false},{"path":"release-manifest.json","size":2049,"binary":false},{"path":"src/index.mjs","size":4232,"binary":false},{"path":"tests/redteam.test.mjs","size":1709,"binary":false}],"readme_html":"

AI Agent Red-Team Benchmark Lab

\n

Reproducible adversarial red-team evaluation suite and containment benchmark for autonomous coding agents.

\n
\n

Overview

\n

AI 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

Core Capabilities

\n\n

Quickstart

\n

Review QUICKSTART.md for zero-friction setup in under 5 minutes.

\n

Verification

\n

Run tests locally using the standard test command:

\n
npm test\n
\n

Licensing

\n

Commercial license granted upon x402 purchase. See LICENSE.md.

","dependencies":[],"licence":{"verdict":"manual"},"scan":{"verdict":"pass","scanner_version":"2026.09.1","at":"2026-09-16T21:28:15.845Z","checks":[{"id":"secrets","tool":"x402git/secrets","tool_version":"2026.09.1","status":"pass","at":"2026-09-16T21:28:15.845Z","findings":0},{"id":"limits","tool":"x402git/limits","tool_version":"2026.09.1","status":"pass","at":"2026-09-16T21:28:15.845Z","findings":0},{"id":"known_vulns","tool":"osv.dev","tool_version":"2026-09-17","status":"pass","at":"2026-09-17T04:00:37.036Z","findings":0,"packages":0},{"id":"known_malware","tool":"osv.dev/MAL","tool_version":"2026-09-17","status":"pass","at":"2026-09-17T04:00:37.036Z","findings":0,"packages":0},{"id":"dep_behaviour","tool":"socket.dev","tool_version":"2026-09-16","status":"findings","at":"2026-09-16T21:28:15.845Z","findings":1,"packages":1},{"id":"capabilities","tool":"x402git/caps","tool_version":"2026.09.1","status":"pass","at":"2026-09-16T21:28:15.845Z","findings":0},{"id":"injection","tool":"x402git/inject","tool_version":"2026.09.1","status":"pass","at":"2026-09-16T21:28:15.845Z","findings":0}],"findings":[{"kind":"behaviour","check":"dep_behaviour","tier":"disclosed","rule_id":"missingLockfile","severity":"LOW","description":"Socket SBOM Resolver (transitive) — no lockfile, so installs are not reproducible","package":{"ecosystem":"generic","name":"Socket SBOM Resolver","direct":false,"dev":false},"source":"socket.dev"}],"capabilities":{"tools":[],"runs":[],"hosts":[],"env":[],"install_runs":false,"summary":"No tools, no hosts, no environment variables, nothing runs at install."},"counts":{"blocking":0,"disclosed":1,"review":0},"advisories_refreshed_at":"2026-09-17T04:00:37.036Z"},"originality":{"blob_overlap_ratio":0,"blobs_seen_elsewhere":0,"blobs_total":21,"nearest_listing":null,"derivative_of":null},"engineering":{"unique_5gram_ratio":0.642,"type_token_ratio":0.484,"effective_code_lines":99,"effective_doc_words":702,"code_files":2,"test_files":2,"padding_suspected":false},"cadence":{"releases":0,"median_days_between_releases":null,"on_time_fraction":null,"days_since_last":null,"score":null,"finished":false},"inventory_sentence":"1 source file · 2 test files · 15 docs · 3 config files","extensions":{"md":16,"mjs":2,"json":3,"(none)":1},"lines_of_code":154,"warnings":["sbom_unavailable"],"repo_meta":{"repo_id":1373094820,"name":"ai-agent-redteam-benchmark-lab","full_name":"genesiscode2026/ai-agent-redteam-benchmark-lab","description":"AI Agent Red-Team Benchmark Lab: Adversarial containment & security evaluation suite.","homepage":null,"topics":["ai-agents","benchmarking","mcp","red-team","security"],"language":"JavaScript","default_branch":"main","size_kb":9,"created_at":"2026-09-16T13:39:51Z","pushed_at":"2026-09-16T13:40:18Z","licence_spdx":null,"open_issues":null,"stars":null,"forks":null,"watchers":null,"archived":false,"private":true,"html_url":null},"owner":{"login":"genesiscode2026","name":null,"avatar_url":"https://avatars.githubusercontent.com/u/329895054?v=4","bio":null,"blog":null,"company":null,"location":null,"twitter_username":null,"followers":null,"public_repos":1,"created_at":"2026-09-16T08:01:39Z","html_url":"https://github.com/genesiscode2026"},"computed_at":"2026-09-16T21:28:24.467Z","analyzer_version":"0.1.0"},"self_reported":{"description":"Adversarial containment and security evaluation suite for AI agents.","trigger_hint":"When requiring verified AI Agent Security functionality in autonomous workflows"}}