SKILLEMALL.ai
RU Sign in

BD yotta-security-testing

元测 —— 有纪律的 AI 安全测试方法论：对已授权目标（自有资产 / SRC 众测 / bug bounty / CTF / 靶场）按 侦察→发现→验证→报告 四阶段做 Web 安全测试（SQLi / XSS / SSRF / XXE / 反序列化 / 命令注入 / 文件上传 / 鉴权与访问控制 / 业务逻辑 / 信息泄露 / 不安全配置 / API 安全 + 漏洞评估与渗透报告方法论），内置 Scope Guard 五道防线（授权清单 scope.json + 目标三层判定 + 内置黑名单 + 操作留痕 + 法律红线），不输出可执行 payload。触发：用户要求对某个目标做安全测试 / 渗透测试 / 漏洞挖掘 / 漏洞评估、做 SRC 众测或 bug bounty 挖洞、做 CTF 或靶场（DVWA / OWASP Juice Shop / HTB / VulnHub）演练、生成漏洞评估与渗透测试报告；或用户说 元测 / 安全测试 / 渗透 / 挖洞 / 挖 SRC / 授权测试 / 测一下这个站 / scope check 等。边界（Do NOT trigger）：无授权目标一律拒绝（授权以 scope.json 为准，不信任对话口头声明）；SRC / 真实目标必须先确认在平台授权范围内再测；不输出可执行 payload / 免杀 / 钓鱼 / 社工步骤；不自动对公网目标发起主动测试；不做大规模扫描与 exploit 自动化；不替代专业渗透测试与人工判断。

ClawHub Agent Skills author: YottaMeta v0.3.0 MIT-0 28 files · 1 script body ≈ 1 215 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

元测 —— 有纪律的 AI 安全测试方法论：对已授权目标（自有资产 / SRC 众测 / bug bounty / CTF / 靶场）按 侦察→发现→验证→报告 四阶段做 Web 安全测试（SQLi / XSS / SSRF / XXE / 反序列化 / 命令注入 / 文件上传 / 鉴权与访问控制 / 业务逻辑 /…

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationSecurityInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
78
Quality 40%
84
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 22

    ✓ No critical or high findings

    Medium and low: 22
    • low Risky intent intent-offensive-security CHANGELOG.md:34
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      对**已授权目标**（自有资产 / SRC 众测·bug bounty / CTF·靶场 / 本地靶机）按
    • low Risky intent intent-offensive-security playbooks/00-methodology.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      > 覆盖：全流程｜源域 vulnerability-assessment + pentest-reporting
    • low Risky intent intent-offensive-security playbooks/00-methodology.md:50
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## 4. 渗透报告方法论（Pentest Report）
    • low Risky intent intent-offensive-security README.md:13
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      <p align="center">Triggers when the user asks for security testing / penetration testing / vulnerability assessment on an
    • low Risky intent intent-offensive-security README.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      authorized target, SRC bug bounty, CTF or lab drills (DVWA / OWASP Juice Shop / HTB / VulnHub), or a vulnerability
      detector
    • low Risky intent intent-offensive-security README.md:15
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      assessment / pentest report; or says 元测 / security test / pentest / bug bounty / authorized test / scope check.</p>
    • low Risky intent intent-offensive-security README.md:44
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      HTB, VulnHub) *and* authorized real targets / SRC bug bounty; real targets must be registered in `scope.json`
      detector
    • low Risky intent intent-offensive-security README.md:70
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 00 | Vulnerability assessment & pentest report methodology | Four stages + report template + SRC practice | Full workflow |
    • low Risky intent intent-offensive-security README.zh-CN.md:10
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      <b>侦察 → 发现 → 验证 → 报告</b> 四阶段，对<b>已授权目标</b>（自有资产 / SRC 众测·bug bounty 授权范围 /
    • low Risky intent intent-offensive-security README.zh-CN.md:12
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      <p align="center">触发场景：用户要求对已授权目标做安全测试 / 渗透测试 / 漏洞评估、挖 SRC 众测或 bug bounty、
    • low Risky intent intent-offensive-security README.zh-CN.md:102
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # 2) 添加授权目标（本地靶场 / CTF / bug bounty / 自有资产 / 显式授权）
    • low Risky intent intent-offensive-security references/faq.md:19
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      未授权公网目标默认拒绝（exit 1），SRC/bug bounty 目标必须先在平台页面确认范围，再用 `scope add --type bug-bounty --target ...` 登记后才测；每轮只测授权范围内的资产。
    • low Risky intent intent-offensive-security references/report-template.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      > 适用：内部漏洞评估报告；SRC / bug bounty 平台提交稿（按平台模板字段映射）。
    • low Risky intent intent-offensive-security references/tutorial.md:29
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # SRC / bug bounty 平台授权范围（以平台 scope 页面为准）
    • low Secrets in code secret-password-literal scripts/test_yotta_security_testing.py:428
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      "evidence": "payload 返回 500；cookie=session=abc123; password=supe…123",
      fixturequoted
    • low Secrets in code secret-password-literal scripts/test_yotta_security_testing.py:519
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      "supe…t99" not in yst.redact_text("password=supe…t99")
      fixturequoted
    • low Secrets in code secret-password-literal scripts/test_yotta_security_testing.py:521
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      yst.redact_text("password=supe…t99"))
      fixturequoted
    • low Secrets in code secret-password-literal scripts/test_yotta_security_testing.py:523
      Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
      yst.redact_text("api_key=tok1…789"))
      fixturequoted
    • low Risky intent intent-offensive-security SKILL.md:4
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: 元测 —— 有纪律的 AI 安全测试方法论：对已授权目标（自有资产 / SRC 众测 / bug bounty / CTF / 靶场）按 侦察→发现→验证→报告 四阶段做 Web 安全测试（SQLi / XSS / SSRF / XXE / 反序列化 / 命令注入 / 文件上传 / 鉴权与访问控制 / 业务逻辑 / 信息泄露 / 不安全配置 / API 安全 + 漏洞评估
    • low Risky intent intent-offensive-security SKILL.md:30
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 对**已授权目标**做 Web 安全测试：自有资产、SRC 众测 / bug bounty 平台授权范围（补天 / 漏洞盒子 / 教育 SRC / HackerOne / Bugcrowd 等）、CTF / 靶场平台、本地靶机；
    • low Risky intent intent-offensive-security SKILL.md:45
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # 2) 添加授权目标（本地靶场 / CTF / bug bounty / 自有资产 / 显式授权）
    • low Risky intent intent-offensive-security SKILL.md:102
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 仅对**已授权目标**使用：自有资产 / SRC·bug bounty 平台授权范围 / CTF·靶场平台 / 本地靶机。

    Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 45/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 28 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1215 tokens
    • 100Progress reporting. Reports progress
    • low 10 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 642: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 28 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    This is mostly a disclosed authorized security-testing helper, but it needs Review because it can persist sensitive targets in local logs/reports and its installer has broad user-level agent installation behavior.
    LLM: suspicious (high) · 9 Sept 2026