SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ghsa-skill-builder

Use when building or updating vulnerability pattern Skills from multiple sources: GitHub Security Advisories (GHSA), HackerOne Hacktivity, or NVD. Triggers on keywords: GHSA, CVE, vulnerability skill, vuln pattern, update skills, security advisory, HackerOne, H1, hacktivity, pentest skill, bug bounty, check for updates.

ClawHub Agent Skills author: yhy v0.1.0 MIT-0 4 files body ≈ 2 297 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 39/100 · Will not run — References files that are not bundled: references/cases.md, scripts/test_vuln_patterns_skills.py, scripts/test_go_vuln_skills.py

GeneratorGitHubSecuritytype 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
86/100
safety, quality, tests
Safety 60%
93
Quality 40%
76
Run on models
none yet
Process rating
F
39/100
Will not run
References files that are not bundled: references/cases.md, scripts/test_vuln_patterns_skills.py, scripts/test_go_vuln_skills.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • low Risky intent intent-offensive-security skill-card.md:14
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Developers and security engineers use this skill to build or refresh vulnerability-audit and pentest skills from advisory, CVE, and public bug bounty data. It guides data fetching, candidate analysis,
  • low Risky intent intent-offensive-security skill-card.md:23
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Mitigation: Invoke it only when intentionally generating or updating vulnerability and pentest skills, and confirm scope, data sources, and credentials before execution. <br>
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    description: "Use when building or updating vulnerability pattern Skills from multiple sources: GitHub Security Advisories (GHSA), HackerOne Hacktivity, or NVD. Triggers on keywords: GHSA, CVE, vulner
    detector
  • low Risky intent intent-offensive-security SKILL.md:10
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **HackerOne Hacktivity**（公开 Bug Bounty 报告）→ 按漏洞类型分类的渗透测试 skills（`pentest-*`）
  • low Risky intent intent-offensive-security SKILL.md:37
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | "用 H1 bug bounty 报告生成渗透测试 skills" | **模式 D：H1 Hacktivity 构建** |
    table
  • low Risky intent intent-offensive-security SKILL.md:38
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | "更新 pentest skills" / "补充 H1 数据" | **模式 D：H1 增量更新** |
    table
  • low Risky intent intent-offensive-security SKILL.md:198
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    从 HackerOne 公开的 Bug Bounty 报告中提取漏洞模式，生成渗透测试 Skills（`pentest-*`）。

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/cases.md
  • warning missing-ref reference to a missing file: scripts/test_vuln_patterns_skills.py
  • warning missing-ref reference to a missing file: scripts/test_go_vuln_skills.py
  • warning missing-ref reference to a missing file: scripts/test_pentest_skills.py

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: references/cases.md, scripts/test_vuln_patterns_skills.py, scripts/test_go_vuln_skills.py
  • 0Tools and files. 4 referenced file(s) missing: references/cases.md, scripts/test_vuln_patterns_skills.py, scripts/test_go_vuln_skills.py
  • 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
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 2 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 44 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2297 tokens

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 321: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 44 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
The skill has a legitimate security-research purpose, but it can be triggered too broadly and tells agents to run local scripts and persist generated skills, so it should be reviewed before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026