SKILLEMALL.ai
GitHub ↗ RU Sign in

BC infrastructure-compliance-auditor

Cross-framework infrastructure security audit across cloud, network, and CI/CD. Use for infrastructure and cloud security audits, security posture assessment, and validating technical controls for SOC 2, ISO 27001, and NIST CSF.

borghei/Claude-Skills Agent Skills author: borghei 10 files · 3 scripts body ≈ 1 968 tokens Open the sourcegithub.com↗ analyzed 8 h ago

Cross-framework infrastructure security audit across cloud, network, and CI/CD.

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerAWSGoogle CloudAzureInfrastructureSecuritytype 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
B
93/100
safety, quality, tests
Safety 60%
94
Quality 40%
92
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Result and completion w 14
40
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Risky intent intent-offensive-security references/access-control-standards.md:449
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Microsegmentation limits lateral movement
    • low Risky intent intent-offensive-security references/access-control-standards.md:503
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. Regular red team exercises to validate
    • low Risky intent intent-offensive-security references/audit-control-catalog.md:809
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | LOG-…001 | Alerts for: failed auth attempts (>5 in 5 min), privilege escalation, data exfiltration patterns | High | SOC 2 CC7.2, ISO 27001 A.12.4.1, PCI-DSS 10.6, NIST CSF DE.CM-1 |
    • low Risky intent intent-offensive-security references/compliance-framework-mapping.md:199
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      3. Annual penetration testing
    • low Risky intent intent-offensive-security references/compliance-framework-mapping.md:248
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **Semi-annually** | Penetration test results | External vendor |
    • low Risky intent intent-offensive-security SKILL.md:98
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Actual penetration testing, vulnerability scanning, or active exploitation -- this skill performs configuration-based assessment, not active testing

    Files scanned: 10. 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 61/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Result and completion. Does not say what the result is
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 28 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1968 tokens
    • 100Running it twice. No mutating operations

    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
    • +2Single-language instructions
    • +3Description length 228: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 28 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)
    • +3All 3 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.