SKILLEMALL.ai
GitHub ↗ RU Sign in

CC performing-external-network-penetration-test

Conduct a comprehensive external network penetration test to identify vulnerabilities in internet-facing infrastructure using PTES methodology, reconnaissance, scanning, exploitation, and reporting.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 8 files · 2 scripts body ≈ 2 473 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Conduct a comprehensive external network penetration test to identify vulnerabilities in internet-facing infrastructure using PTES methodology…

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureGitHubSecurityAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
82
Quality 40%
75
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
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 · 18

    ✓ No critical or high findings

    Medium and low: 18
    • low Risky intent intent-offensive-security assets/template.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # External Network Penetration Test — Report Template
    • low Risky intent intent-offensive-security assets/template.md:8
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Assessment Type | External Network Penetration Test |
    • low Risky intent intent-offensive-security assets/template.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Authorization ID | [PENTEST-YYYY-EXT-NNN] |
    • low Risky intent intent-offensive-security assets/template.md:21
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      [Organization Name] engaged [Testing Company] to perform an external network penetration test against its internet-facing infrastructure. The assessment was conducted between [dates] following the PTE
      detector
    • low Risky intent intent-offensive-security assets/template.md:95
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - PTES (Penetration Testing Execution Standard)
    • low Risky intent intent-offensive-security references/api-reference.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # API Reference — Performing External Network Penetration Test
    • low Risky intent intent-offensive-security references/standards.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Standards and Frameworks — External Network Penetration Testing
    • low Risky intent intent-offensive-security references/standards.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### PTES (Penetration Testing Execution Standard)
    • low Risky intent intent-offensive-security references/standards.md:6
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Website: http://www.pentest-standard.org/
    • low Risky intent intent-offensive-security references/standards.md:8
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Best for: Comprehensive network penetration testing engagements
    • low Risky intent intent-offensive-security references/standards.md:26
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Framework | Requirement | Pentest Frequency |
    • low Risky intent intent-offensive-security references/workflows.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Workflows — External Network Penetration Testing
    • low Risky intent intent-offensive-security references/workflows.md:33
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      6. Attempt lateral movement from compromised hosts
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Conduct a comprehensive external network penetration test to identify
    • low Risky intent intent-offensive-security SKILL.md:9
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - external-pentest
    • low Risky intent intent-offensive-security SKILL.md:34
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Performing External Network Penetration Test
    • low Risky intent intent-offensive-security SKILL.md:38
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      An external network penetration test simulates a real-world attacker targeting an organization's internet-facing assets such as firewalls, web servers, mail servers, DNS servers, VPN gateways, and clo
    • low Risky intent intent-offensive-security SKILL.md:43
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - When conducting security assessments that involve performing external network penetration test

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 51/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 14 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2473 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 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
    • -43 reference files, but SKILL.md never points to them: the model will not open them
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 198: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (10 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.