SKILLEMALL.ai
GitHub ↗ RU Sign in

CC cis-controls

Expert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data protection, secure configuration, account management, access control, continuous vulnerability management, audit log management, email and web browser protections, malware defenses, network infrastructure management, network monitoring and defense, application software security, incident response, penetration testing, and CIS Controls mapping to NIST CSF, ISO 27001, SOC 2, and CMMC. Use for any question about CIS Controls, CIS Benchmarks, Implementation Groups, or prioritized cyber hygiene for any organization size.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 6 files body ≈ 4 017 tokens Open the sourcegithub.com↗ analyzed 75 min ago

Expert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory…

As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerInfrastructureSecuritytype 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
86/100
safety, quality, tests
Safety 60%
84
Quality 40%
88
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
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 · 16

    ✓ No critical or high findings

    Medium and low: 16
    • low Risky intent intent-offensive-security README.md:11
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      For each of the 18 controls, the skill provides safeguard-level guidance: what the control requires, why it matters in terms of real attack scenarios, how to implement it with practical tooling exampl
    • low Risky intent intent-offensive-security README.md:62
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      - _"Draft a Penetration Testing Policy that satisfies CIS Control 18."_
      quoted
    • low Risky intent intent-offensive-security README.md:71
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Incident Response and Penetration Testing
    • low Risky intent intent-offensive-security README.md:73
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      - _"Design our annual penetration testing program per CIS Control 18."_
      quoted
    • low Risky intent intent-offensive-security README.md:160
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **All 18 controls** — full descriptions with key safeguards called out for each IG level, from Control 1 (Asset Inventory) through Control 18 (Penetration Testing)
    • low Risky intent intent-offensive-security references/implementation-guidance.md:111
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Penetration Testing (Control 18)**
    • low Risky intent intent-offensive-security references/implementation-guidance.md:114
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Red team exercises with full adversary simulation — beyond base CIS scope
    • low Risky intent intent-offensive-security references/implementation-guidance.md:115
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Purple team exercises — combine red team and SOC for knowledge transfer
    • low Risky intent intent-offensive-security references/implementation-guidance.md:129
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Bug bounty program or responsible disclosure policy — related to 16.4
    • low Risky intent intent-offensive-security references/safeguards-detail.md:248
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 17.7 (IG2): Conduct tabletop exercises; include ransomware scenarios
    • low Risky intent intent-offensive-security references/safeguards-detail.md:250
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Control 18: Penetration Testing
    • low Risky intent intent-offensive-security references/safeguards-detail.md:251
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 18.2 (IG2): Annual external penetration test by qualified third party
    • low Risky intent intent-offensive-security references/safeguards-detail.md:252
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - 18.5 (IG3): Quarterly internal pen tests; red team exercises
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      description: "Expert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data pro
      quoted
    • low Risky intent intent-offensive-security SKILL.md:133
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **CIS Control 18: Penetration Testing**
    • low Risky intent intent-offensive-security SKILL.md:135
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - Key Safeguards: 18.1 Establish/maintain a penetration testing program; 18.2 Perform periodic external penetration tests; 18.3 Remediate penetration test findings; 18.4 Validate security measures; 18
      detector

    Files scanned: 6. 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 54/100

    • 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. 10 mutating operations with no state check
    • 40Consistency. Frontmatter name (cis-controls) differs from the folder (cis-controls-tanaji-hemant-naik)
    • 60Result and completion. Output format stated, no completion criterion
    • 70Execution cost. Instruction body is 4017 tokens
    • 100Tools and files. No external tools needed
    • 100Steps. 48 steps
    • 100Progress reporting. Reports progress

    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)
    • +4No input/output examples
    • +2Single-language instructions
    • +3Description length 704: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 48 items
    • +3Output format is stated explicitly
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.