SKILLEMALL.ai
GitHub ↗ RU Sign in

AC security-tester

Security testing for web applications and APIs based on OWASP standards. Identify common vulnerabilities (injection, auth bypass, XSS, CSRF, IDOR), generate security test cases, analyze scan results, and write security test reports. Follows OWASP Testing Guide v4.2, OWASP Top 10 (2021), and CWE classifications. Use when: (1) security testing web apps or APIs, (2) writing security test cases, (3) analyzing vulnerability scan results, (4) OWASP Top 10 verification, (5) authentication/authorization testing, (6) input validation testing, (7) "安全测试", "漏洞测试", "OWASP", "XSS测试", "SQL注入", "渗透测试", "权限测试", "越权测试", "IDOR", "CSRF". NOT for: code-level static analysis (use SAST tools), infrastructure penetration testing (use dedicated pentest tools), or compliance auditing (use GRC tools).

ClawHub Agent Skills author: zhanghengyi1986-afk v1.0.0 MIT-0 4 files body ≈ 1 273 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ReferenceSecuritytype 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
A
91/100
safety, quality, tests
Safety 60%
93
Quality 40%
89
Run on models
none yet
Process rating
C
52/100
Has gaps
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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Risky intent intent-offensive-security references/owasp-top10-tests.md:23
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      ### Privilege Escalation
      fixture
    • low Risky intent intent-offensive-security SKILL.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      testing (use dedicated pentest tools), or compliance auditing (use GRC tools).
    • low Risky intent intent-offensive-security SKILL.md:27
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | A01 | Broken Access Control | CWE-284 | IDOR, privilege escalation, force browse, CORS |
    • low Exfiltration net-credential-use SKILL.md:46
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -H "Authorization: Bearer $USER_A_TOKEN" \
      security skill
    • low Risky intent intent-offensive-security SKILL.md:50
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Horizontal privilege escalation
    • low Exfiltration net-credential-use SKILL.md:51
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -H "Authorization: Bearer $NORMAL_USER_TOKEN" \
      security skill
    • low Exfiltration net-credential-use SKILL.md:64
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -X DELETE -H "Authorization: Bearer $READONLY_TOKEN" \
      security skill

    Files scanned: 4. 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 52/100

    • 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
    • 50Steps. 2 steps
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1273 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +3No numbered steps or checklist
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 786: enough signal without eating the budget
    • +4Structure: 10 headings
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    This is a legitimate security testing guide, but it needs review because its copyable examples could stress, alter, or probe real systems without explicit authorization safeguards.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026