Skip to content
Agentmart
Submit a tool
This entry duplicates pentest-blackboard, which is the one we list in search.

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 Kxiandaoyan

IndexedApache-2.0★ 33
Write a review

Chalk Labs

Need help deploying pentest-blackboard?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/kxiandaoyan-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.

We use your email only for this newsletter. Privacy

About

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.

Use cases: security, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

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
109 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。**

## 与经验总结的分工

- 本项目可复现上下文 → 只写黑板 / 漏洞库
- 跨项目可复用的检测顺序 → 不要在会话里写 SKILL.md;收尾见 experience-closeout
- 系统可能在可交付完成后生成经验草稿;未批准前 skills/ 不会变

## 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(本地优先,0 命中完整回退)**:识别任何组件/框架/版本/中间件 → 暂停利用 → 先 `skill local-corpus-cve` + `zvec_grep_search` 查本机近 5 年 CVE 语料 → 有命中记 `tentative` Fact 并核对版本(要利用时先查本地实战 POC 层,再按 CVE-ID 定向外网);**本地 0 命中 → 完整执行 `component-vuln-intel` 的外网序列(与原版一致,一步不少,本地只是加速层不是截断层)** → 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 Kxiandaoyan/CyberStrikeAI, Apache-2.0.

Signals

Stars
33
Forks
11
Open issues
0
Last commit (this folder)
Sep 7, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from Kxiandaoyan

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get pentest-blackboard running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying pentest-blackboard?

CallGet help
Cite this page

pentest-blackboard skill. Agent Mart. https://agentmart.dev/skills/kxiandaoyan-pentest-blackboard (last updated 2026-10-24)