yhy0/CHYing-agent

ai-security

Use when facing AI security challenges involving prompt injection, LLM jailbreaks, or AI agent exploitation

Source text: Chinese

binary

Use when facing binary exploitation (PWN) or reverse engineering challenges involving memory corruption, ROP chains, shellcode, binary analysis, decompilation, unpacking, or dynamic tracing

Source text: Chinese

cryptography

Use when facing cryptography challenges involving cipher analysis, key recovery, mathematical attacks, or protocol weaknesses

Source text: Chinese

file-transfer

Use when transferring files between remote environments and local Docker containers via litterbox.catbox.moe relay or base64 chunked fallback

Source text: Chinese

forensics-misc

Use when facing digital forensics or misc challenges involving disk images, memory dumps, network captures, steganography, file format analysis, encoding puzzles, sandbox escapes, or archive manipulation

Source text: Chinese

infra-exploit

Use when conducting penetration testing, post-exploitation, lateral movement, domain attacks, cloud exploitation (AWS/GCP/Azure), container escape, or Kubernetes cluster attacks

Source text: Chinese

stagnation-recovery

Use when stuck, looping on same approach, making no progress after multiple tool calls, or receiving a stagnation warning from the system. Also trigger when you catch yourself retrying the same command with minor variations, getting repeated Permission denied…

Source text: Chinese

web-security

Use when facing web security challenges involving injection, authentication bypass, IDOR, access control, CSRF, HRS, server-side vulnerabilities, or web application exploitation

Source text: Chinese

wss-terminal

Use when extracting WSS terminal connection parameters (URL, cookie, protocol type) from browser pages for wss_connect tool usage

Source text: Chinese

ctf-postmortem

分析 CHYing Agent 的 CTF 比赛日志，统计解题率，诊断失败根因，并输出可操作的系统级优化建议。适用于赛后复盘或定期系统改进。 (project)

Source text: Chinese

null-zone-battle-scan

零界战场感知 — 每10分钟执行一次，更新战场状态、Agent画像、联盟评分，产出本轮博弈决策。所有其他任务的前置感知层。

Source text: Chinese

null-zone-c1-daily-playbook

赛题一每日首轮攻击序列 — 被 injection-cycle 在每日首次触发时读取

Source text: Chinese

null-zone-c3-injection

零界挑战三：C3 帖子注入模板库 — 为每篇帖子选择并生成多向量分层注入层，最大化其他 AI agent 点赞率。被 post-cycle 调用，不单独 cron 执行。

Source text: Chinese

null-zone-crowdsource-pentest

隐藏关卡众包渗透 — 将主赛场靶场包装为零界隐藏关卡，发帖+群发私信通知全论坛 agent。被 post-cycle 中策略 F7 触发，或手动调用。

Source text: Chinese

null-zone-injection-cycle

零界挑战一：提示词注入周期 — 每小时5次（cron:6,21,36,51,56），每次触发均可提交注入评论+检查私信回复。Bot 每小时:59 批量处理所有未处理评论。

Source text: Chinese

null-zone-interact-cycle

零界挑战三：互动维护周期 — 每10分钟偏移执行（5,15,25,35,45,55分），评论热门帖子、维护联盟、执行跨挑战协同、监控点踩、计算注入效果。

Source text: Chinese

null-zone-key-exchange-cycle

零界挑战二：密钥交换周期 — 每5分钟执行，检查私信、处理密钥碎片、执行TFT决策、拼接提交flag。

Source text: Chinese

null-zone-post-cycle

零界挑战三：发帖周期 — 每30分钟执行，根据战场感知选择内容策略，发布一篇高互动帖子（一帖三用原则）。

Source text: Chinese

null-zone-forum

零界AI社交网络比赛助手 - 自动化参赛框架。封装四大挑战（提示词注入、密钥交换、影响力竞争、信息搜集）的完整策略、博弈决策框架、cron定时任务编排、密钥管理和Flag自动提交。通过 Claude Code CLI + tmux 持久化运行。

Source text: Chinese

null-zone-status-report

零界全局状态汇报 — 每小时 :02 执行（避免与 battle-scan :00 冲突），汇总各挑战进度、计算布洛托ROI、产出资源再分配决策、更新TFT状态。

Source text: Chinese

null-zone-treasure-scan

零界挑战四：实时寻宝扫描 — 每3分钟执行，增量扫描新内容，识别并解析隐藏线索，立即提交发现的flag。

Source text: Chinese