{"name":"FakeLiang","repo":"cxm947/FakeLiang","url":"https://midorreal.com/project/cxm947-fakeliang","repository":"https://github.com/cxm947/FakeLiang","description":"基于攻击图的靶场自动验证，多agent框架，kali MCP，自动化编排，POC生成。","facts":{"language":{"value":"Python","source":"https://github.com/cxm947/FakeLiang","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/cxm947/FakeLiang/releases","checked":"19 Nov 2026"},"contributors":{"value":"2","source":"https://github.com/cxm947/FakeLiang/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/cxm947/FakeLiang","checked":"22 Nov 2026"}},"stars":235.0,"writeup":{"what_it_is":"FakeLiang is a multi-agent framework that automatically validates attack graph paths in a lab environment. It reads attack graphs (MulVAL or JSON format), asset information, and host-IP mappings, then uses a Planner, Executor, and Verifier agent to step through nodes, verify preconditions, execute exploits, and validate outcomes with traceable evidence.","audience":"Security researchers and penetration testers validating attack graphs","claims":[{"kind":"specific","claim":"Supports MulVAL TXT and compiled JSON attack graph formats","excerpt":"MulVAL TXT 或已编译 JSON","status":"not_checked"},{"kind":"specific","claim":"Three-agent architecture with Planner, Executor, and Verifier roles","excerpt":"Planner、Executor 与 Verifier 协作","status":"not_checked"},{"kind":"specific","claim":"Saves traceable evidence including call parameters, stdout, stderr, and model transcripts","excerpt":"保存调用参数、标准输出、错误输出与模型转录，支持逐步复核","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-15"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":4,"reality":11,"gap":-7,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-12T02:01:07+00:00","text":"Repository created","source":"https://github.com/cxm947/FakeLiang"}],"cite":"FakeLiang is a GitHub project at https://github.com/cxm947/FakeLiang written mainly in Python, described there as \"基于攻击图的靶场自动验证，多agent框架，kali MCP，自动化编排，POC生成。\".","attribution":"Data from Mid or Real, https://midorreal.com/project/cxm947-fakeliang, checked 22 November 2026. Attribution with a link is required.","still_real":null}