SKILLEMALL.ai
GitHub ↗ RU Sign in

BC threat-modeling

Threat model, security audit, find vulnerabilities, check security of my app, risk assessment, penetration test prep, analyze attack surface, what could an attacker exploit. Use this skill whenever a user wants holistic security analysis of a codebase, application, or project. MUST be invoked instead of analyzing security yourself — it runs a specialized 8-phase STRIDE workflow producing professional deliverables you cannot generate alone: risk assessment reports, DFD diagrams, threat inventories, attack path validation, mitigation plans, and pentest plans. Trigger on: 威胁建模, 安全评估, 渗透测试, 安全分析, 安全审计, 安全检查, 风险评估. NOT for: fixing one specific bug, adding one security feature (rate limiting, CORS), writing tests, CI/CD setup, or debugging errors.

ClawHub Agent Skills author: fr33d3m0n v3.1.0 MIT-0 80 files · 1 script body ≈ 4 772 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerSoftware developmentData and analyticsSecuritytype 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
76/100
safety, quality, tests
Safety 60%
64
Quality 40%
95
Run on models
none yet
Process rating
C
60/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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 · 36

    ✓ No critical or high findings

    Medium and low: 36
    • low Risky intent intent-offensive-security docs/KNOWLEDGE-ARCHITECTURE-v5.2.md:588
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      phase: "Lateral Movement"
      quoted
    • low Risky intent intent-offensive-security docs/KNOWLEDGE-ARCHITECTURE-v5.2.md:675
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - "Penetration test confirms fix effectiveness"
      detector
    • low Risky intent intent-offensive-security docs/Skillset-threat-modeling-tour-v5.md:25
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Verification Phase**: Dynamic Application Security Testing (DAST), Interactive Application Security Testing (IAST), and manual penetration testing are executed at this stage. While these techniques
    • low Risky intent intent-offensive-security docs/Skillset-threat-modeling-tour-v5.md:50
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      │   │          │  Threat     │      SAST/Code Review │  IAST/DAST/Pentest/     │    │ │
    • low Risky intent intent-offensive-security docs/Skillset-threat-modeling-tour-v5.md:62
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      │   • Security testing, penetration testing, and compliance audits—high-investment     │
    • low Risky intent intent-offensive-security docs/Skillset-threat-modeling-tour-v5.md:152
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Effective STRIDE analysis requires both system architecture understanding and offensive/defensive practical experience. To assess API endpoint privilege escalation risks, analysts must understand:
    • low Risky intent intent-offensive-security docs/Skillset-threat-modeling-tour-v5.md:184
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Security activities can be embedded in testing phase**: Penetration testing, security audits, and compliance checks are executed here
    • low Secrets in code secret-high-entropy-token knowledge/compliance-mappings.yaml:632
      High-entropy token-like string (may be an id, hash or a credential)
      A05_…on:
    • low Risky intent intent-offensive-security knowledge/security-controls/control-set-10-data-protection.md:58
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Avoid making accounts database owners to prevent privilege escalation.
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-authentication.md:145
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      It is generally not a good idea to use this method for widely and publicly available websites that will have an average user. For example, it wouldn't be a good idea to implement this for a website li
      quoted
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-authentication.md:254
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Password Spraying | Testing a single weak password against a large number of different accounts.|
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-authentication.md:258
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      The following sections will focus primarily on preventing brute-force attacks, although these controls can also be effective against other types of attacks. For further guidance on defending against c
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-credential-stuffing-prevention.md:7
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      This cheatsheet covers defences against two common types of authentication-related attacks: credential stuffing and password spraying. Although these are separate, distinct attacks, in many cases the
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-credential-stuffing-prevention.md:13
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Password Spraying | Testing a single weak password against a large number of different accounts.|
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-credential-stuffing-prevention.md:17
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      [Multi-factor authentication (MFA)](Multifactor_Authentication_Cheat_Sheet.md) is by far the best defense against the majority of password-related attacks, including credential stuffing and password s
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-credential-stuffing-prevention.md:37
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Where it is not possible to implement MFA, there are many alternative defenses that can be used to protect against credential stuffing and password spraying. In isolation none of these are as effectiv
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-credential-stuffing-prevention.md:57
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      It must be emphasised that this **does not** constitute multi-factor authentication (as both factors are the same - something you know). However, it can still provide a useful layer of protection agai
    • low Secrets in code secret-high-entropy-token knowledge/security-controls/references/reference-set-01-jwt-java.md:26
      High-entropy token-like string (may be an id, hash or a credential)
      TJVA…HgQ
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-01-multifactor-authentication.md:23
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      MFA is by far the best defense against the majority of password-related attacks, including brute-force, [credential stuffing](Credential_Stuffing_Prevention_Cheat_Sheet.md) and password spraying, with
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-02-authorization.md:95
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Based on this URL, one could reasonably assume that the application will return a listing of transactions and that the transactions returned will be restricted to a particular account - the account in
    • low Risky intent intent-offensive-security knowledge/security-controls/references/reference-set-02-authorization.md:135
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Unit and integration testing are essential for verifying that an application performs as expected and consistently across changes. Flaws in access control logic can be subtle, particularly when requir
    • low Risky intent intent-offensive-security README.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assessment, threat modeling, security analysis, security audit, and penetration testin
    • low Risky intent intent-offensive-security README.md:21
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Backported SM2 state machine from next-gen AI-Native penetration testing system named "Cobweb" for problem-solving in depth
    • low Risky intent intent-offensive-security README.md:133
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Mode 6: Backward Integration (Penetration Testing)
    • low Risky intent intent-offensive-security README.md:135
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Attack path and POC design support for pentesting.
    • low Risky intent intent-offensive-security README.md:150
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **Vulnerability Analysis** | Code / Description | Attack path + POC | Code review / Pentest |
    • low Risky intent intent-offensive-security SKILL.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      assessment, penetration test prep, analyze attack surface, what could an attacker exploit.
    • low Risky intent intent-offensive-security SKILL.md:11
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      plans, and pentest plans.
    • low Risky intent intent-offensive-security SKILL.md:24
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assessment, threat modeling, security testing, penetration testing, and compliance che
    • low Risky intent intent-offensive-security SKILL.md:278
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | TestCase | TC-{Seq:03d} | P8 | Penetration test cases |
    • low Risky intent intent-offensive-security WORKFLOW.md:218
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | P5 | 4 | Architecture Perspective, Code Implementation Perspective, Security Testing Perspective, Penetration Testing Perspective |
    • low Risky intent intent-offensive-security WORKFLOW.md:219
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | P6 | 4 | Architect, Attack Path Analyst, Vulnerability Researcher, Penetration Test Planner |

    A further 4 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 80. 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 60/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 3 mutating operations with no state check
    • 40Consistency. Frontmatter name (threat-modeling) differs from the folder (skill-threat-modeling)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Execution cost. Instruction body is 4772 tokens
    • 100Steps. 31 steps
    • 100When it triggers. States when to use and when not to
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 14 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
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 753: enough signal without eating the budget
    • +4Structure: 32 headings
    • +3Step-by-step instructions: 31 items
    • +3Output format is stated explicitly
    • +4Has examples (14 code blocks)
    • +4Reference files are cited in the instructions (2 of 9)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.

    External checks

    ClawHub: suspicious
    This skill is a legitimate threat-modeling tool, but it also steers agents toward actionable exploit and penetration-test workflows without strong authorization or sandbox limits.
    LLM: suspicious (high) · VirusTotal: benign · 28 May 2026