pentest-blackboard
CyberStrikeAI 项目黑板:跨会话 Fact 图(SQLite)+ upsert_project_fact/record_vulnerability 边渗透边记录节奏、关系边 links、confidence、与多代理协调落库。Use when managing project facts…
Skill by AIPentest
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aipentest-pentest-blackboard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, writing, agent-memory, security-scanning
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/pentest-blackboard
What's inside
- Skill name
pentest-blackboard- Description
- CyberStrikeAI 项目黑板:跨会话 Fact 图(SQLite)+ upsert_project_fact/record_vulnerability 边渗透边记录节奏、关系边 links、confidence、与多代理协调落库。Use when managing project facts, blackboard index, writing evidence, or avoiding context-loss after compression.
- License
- Apache-2.0
- Instructions
- 103 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 项目黑板(与本产品对齐)
> 状态落在**已绑定项目**的 SQLite 黑板,不依赖对话上下文,也不使用 `.pentest/` 目录。
> 系统自动注入「项目黑板索引」(仅 `fact_key` + summary);**摘要不足必须 `get_project_fact`,禁止凭摘要臆造细节。**
## 原语与分工(产品模型)
| 概念 | 产品落点 | 规则 |
|------|----------|------|
| **Fact** | `project_facts`(`upsert_project_fact`) | 同 `fact_key` **覆盖更新**;非正式漏洞条目。`confidence`: `confirmed` \| `tentative` \| `deprecated` |
| **关系边** | `project_fact_edges`(upsert 的 `links`) | 结构化攻击图;finding/chain/exploit/poc **必须**带 links |
| **可交付漏洞** | `record_vulnerability` | 与 Fact **可各记一次**:Fact=复现上下文,漏洞=正式 finding |
| **探索方向** | 本轮计划 / 协调者委派 / plantask(若启用) | **不是**独立 Intent 表;待验证方向用 `confidence=tentative` 的 `note/` 或先不落库、验证后再写 |
| **人类注入** | 用户消息 / HITL 审批 | 直接吸收进决策;不必写成 Hint 原语 |
### Fact vs 漏洞
- **环境/目标/认证等认知** → 只写 Fact(`target/` `auth/` `infra/` `business/`)
- **发现与利用上下文** → Fact(`finding/` `chain/` `exploit/` `poc/`)+ body 填满攻击链
- **可交付 findings** → `record_vulnerability`(标题、严重程度、类型、目标、POC、影响、修复);记前可用 `list_vulnerabilities` 查重
## 强制节奏:边渗透边记录
勿等会话结束再批量写入。
1. 每**确认**一条新认知(开放端口/服务版本、入口路径、认证态或凭据特征、可利用点或攻击面变化)→ **立即** `upsert_project_fact`(同 key 覆盖)。
2. 每**验证**出一条可复现漏洞(含 POC/影响)→ **立即** `record_vulnerability`;与事实可各记一次。
3. 继续下一步前优先落库,避免上下文压缩丢细节。
4. **未绑项目**:说明无法写黑板,仍在本轮保留证据摘要。
5. **协调者**:子任务返回新认知/漏洞时由协调者写入,勿假定子代理已记。
6. **子代理无工具时**:交付物末尾给「待落库」条目(建议 `fact_key`、summary、body/POC 要点),供协调者立即写入。
## 工具速查
| 工具 | 用途 |
|------|------|
| `upsert_project_fact` | 写入/更新事实(含 body、confidence、links) |
| `get_project_fact` | 按 key 取完整 body(索引不够时必调) |
| `list_project_facts` / `search_project_facts` | 检索黑板 |
| `deprecate_project_fact` / `restore_project_fact` | 误报废弃 / 恢复 |
| `record_vulnerability` | 可交付漏洞 |
| `list_vulnerabilities` / `get_vulnerability` | 查重与详情 |
前置:**当前对话已绑定项目**(否则工具报错)。
## 写入规范
### fact_key / category
- 格式:小写 `category/slug`(如 `target/primary_domain`、`finding/sqli-login`)
- 环境:`target` \| `auth` \| `infra` \| `business`
- 发现利用:`finding` \| `chain` \| `exploit` \| `poc`(另可用 `note`)
- **同一发现保持同一 `fact_key` 覆盖**,勿拆成多个 key 导致上下文丢失
### summary / body / confidence
- **summary**(索引用一行):须含「什么 + 在哪 + 如何触发/验证」,禁止只写「存在 SQLi」
- **body**:完整可复现上下文(索引不含 body)。发现/利用类必含:入口 → 步骤 → 原始请求/响应或命令 → 现象 → 证据 → `related_vulnerability_id`(若有)
- **confidence**:有证据钉死 → `confirmed`;仅线索/待验证 → `tentative`;误报 → `deprecate_project_fact`(或 `deprecated`)
- 更新时若省略 body,保留库中已有 body(可只改 summary)
### 关系边 links(写入 finding/chain/exploit/poc 时必填)
- 推荐 `from`:来源 fact → 当前 `fact_key`
- 最少:finding 至少 1 条 `{from: target/*, type: discovered_on}`;在 finding 上挂 exploit 用 `{from: exploit/*, type: exploits}`
- 常用 type:`discovered_on` \| `depends_on` \| `leads_to` \| `enables` \| `exploits` \| `contains` \| `part_of` \| `supports`
- **省略 links** = 保留已有边;传入 links = **替换**全部入边
## 工作方式(对齐本产品编排)
不设 Bootstrap/Reason/Explore 磁盘状态机。按当前运行模式推进,但**读写黑板的纪律不变**:
| 模式 | 黑板用法 |
|------|----------|
| 单代理 / deep | 边干边 `upsert_project_fact`;读索引不够则 `get_project_fact` |
| plan_execute | 计划步骤产出认知后立即落库;重规划前 `list/search_project_facts` |
| supervisor | 协调者汇总子代理「待落库」并写入;子代理无工具则结构化交付 |
卡住时:换边/换起点/换攻击域;用 `search_project_facts` 重审已有 Fact,避免重复死路。负结果也要落库(见验证铁律 skill)。
## 行为触发器(纪律)
每步必检(不检=违反验证铁律):
1. **识别→搜**:识别任何组件/框架/版本/中间件 → 暂停利用 → 立即执行 `component-vuln-intel` 全部命令(browser_navigate+terminal curl,7 个步骤全做)→ 结果用 `tentative` Fact 或本轮计划跟踪 → 搜完才继续。不搜就说「无已知漏洞」=幻觉;**验证后**再 `confirmed` / `record_vulnerability`。
2. **拒绝→换路**:收到 403/429/超时/RST/WAF 拦/CDN 502/限流/空响应 → 禁止同条件重试 → 立即换路序列:SOCKS5 代理→换 UA→加 XFF→换协议(WS/DNS)→换端口→编码变异(完整代理获取/验证见 `proxy-tool-bootstrap`)→ 全换仍不通才写负结果 Fact(`confirmed` + body 写清已测条件)换面。
3. **新认知→横向**:拿到凭据/域名/IP/路径 → 立即横向喷:凭据全服务复用 / 新域名全端口扫 / IP 反查同站 → 不等人指示自动扩展攻击面,并 `upsert_project_fact`(如 `auth/cred-*`、`target/related-*`)。有凭据不喷=遗漏。
违反判定:不搜就说「无已知漏洞」=幻觉;被拦不换路=放弃;有凭据不喷=遗漏 → 均违反验证铁律。
## 证据 / 战利品 / 改动
| 原「磁盘」概念 | 本产品做法 |
|----------------|------------|
| evidence/ | Fact `body` + `record_vulnerability` 的证明字段 + 工具执行记录;大文件放会话/项目 workspace |
| loot/ | 凭据特征写入 `auth/` Fact(注意脱敏与授权范围);完整秘密按项目策略处理 |
| changelog.md | 写入型改动在回复中台账化,并可 `note/change-*` Fact 记录主机/类型/位置/回滚命令 |
## 与验证铁律的衔接
详见 `pentest-verification`:搜索≠漏洞;无证据不写 `confirmed`;禁止空泛「可能/疑似」当结论;验证失败写负结果 Fact。From AIPentest/CyberStrikeAI, Apache-2.0.
More from AIPentest/CyberStrikeAI
- 0.851score
attack-surface-recon
AIPentest
侦察/攻击面测绘:被动whois/amass/crt.sh/FOFA/Shodan,主动subfinder/httpx/naabu/katana/nuclei,DNS地域/CDN/Nginx catch-all/宝塔/UniApp指纹。开局第一动作,认知写入项目黑板。Use when starting recon…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
capability-primitive-search
AIPentest
能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
cloud-attack-methods
AIPentest
云攻击:元数据API,S3/K8s,AWS/Azure/GCP身份提权,MinIO矩阵,阿里云FC,ChengZi SDK解密。Use when attacking cloud metadata, IAM, K8s, MinIO, Aliyun FC, or cloud post-ex.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
component-vuln-intel
AIPentest
联网情报收集:识别组件后必做CVE/搜索引擎/中文社区/GitHub PoC/资产引擎/即时情报/依赖扩展+受阻换路。Use when a framework/component/version is identified and must search before exploit.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
post-exploitation
AIPentest
后渗透/提权+凭据破解+密码学:反弹shell,Linux/Windows提权,横向,隧道,免杀,C2持久化,hashcat/Padding Oracle/hash长度扩展。Use when post-exploitation, privilege escalation, lateral movement, or…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
proxy-tool-bootstrap
AIPentest
自找代理+工具自举:SOCKS5/HTTP/Tor换路序列,工具Python自举,字典自生成,OOB基础设施。Use when blocked by 403/429/WAF/timeout, missing tools, or needing OOB confirmation.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
specialized-attack-playbooks
AIPentest
专题实战利用:GoEdge私钥导出,灰产CDN取证,ARP MITM,CDN→S3 STS链,宝塔+UniApp,AI IDE API反代,OCS+MinIO;含references/scripts支持文件索引。Use when applying specialized playbooks for GoEdge…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
pentest-agent-os
AIPentest
渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法 (联网情报/Web/认证/服务端/源码/社工/后渗透/二进制/内网域/云/区块链/AI/无线/硬件)+0day+…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
binary-mobile-reversing
AIPentest
APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
web-attack-methods
AIPentest
Web全栈攻击:SQLi/命令注入/SSTI/XSS/SSRF/NoSQL,认证JWT/OAuth/SAML,LFI/上传,Tomcat/WS/STOMP/XFF/PATH_INFO/CDN502/网宿JS挑战绕过。Use when testing Web injection, auth bypass…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
zero-day-discovery
AIPentest
0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.
SkillAFreshness: A★ 8KClaude Code +9 - 0.850score
cyberstrike-eino-demo
AIPentest
满配示例技能包:SKILL.md + scripts/、references/、assets/ 等可选目录;验证 Eino skill 与 HTTP 包内路径(仅授权安全测试与教学)。
SkillAFreshness: A★ 8KClaude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 8,008
- Forks
- 1,682
- Open issues
- 50
- Last commit (this folder)
- Jul 29, 2026 (3 months ago)
- Last release
- Oct 16, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/AIPentest/CyberStrikeAI
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from AIPentest
- 0.851score
attack-surface-recon
AIPentest
侦察/攻击面测绘:被动whois/amass/crt.sh/FOFA/Shodan,主动subfinder/httpx/naabu/katana/nuclei,DNS地域/CDN/Nginx catch-all/宝塔/UniApp指纹。开局第一动作,认知写入项目黑板。Use when starting recon…
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
binary-mobile-reversing
AIPentest
APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
capability-primitive-search
AIPentest
能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
cloud-attack-methods
AIPentest
云攻击:元数据API,S3/K8s,AWS/Azure/GCP身份提权,MinIO矩阵,阿里云FC,ChengZi SDK解密。Use when attacking cloud metadata, IAM, K8s, MinIO, Aliyun FC, or cloud post-ex.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
component-vuln-intel
AIPentest
联网情报收集:识别组件后必做CVE/搜索引擎/中文社区/GitHub PoC/资产引擎/即时情报/依赖扩展+受阻换路。Use when a framework/component/version is identified and must search before exploit.
SkillAFreshness: A★ 8KClaude Code +9 - 0.851score
post-exploitation
AIPentest
后渗透/提权+凭据破解+密码学:反弹shell,Linux/Windows提权,横向,隧道,免杀,C2持久化,hashcat/Padding Oracle/hash长度扩展。Use when post-exploitation, privilege escalation, lateral movement, or…
SkillAFreshness: A★ 8KClaude Code +9
Cite this page
pentest-blackboard skill. Agent Mart. https://agentmart.dev/skills/aipentest-pentest-blackboard (last updated 2026-10-24)