SKILLEMALL.ai
GitHub ↗ RU Sign in

AC iso-27001-internal-audit

Run an ISO 27001 internal audit. Walk through controls by domain, identify gaps, collect evidence, and generate findings with corrective action recommendations. Uses NIST SP 800-53 (public domain) as canonical reference. Use when user says "run internal audit," "ISO 27001 audit," "control assessment," "audit findings," or "ISMS assessment."

ClawHub Agent Skills author: Steven Obiajulu v0.1.0 MIT-0 12 files body ≈ 3 269 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerInfrastructuretype 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
95/100
safety, quality, tests
Safety 60%
95
Quality 40%
96
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Risky intent intent-offensive-security rules/change-management.md:87
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Define and implement security testing processes during development and before production deployment. This includes functional security testing, vulnerability scanning, and penetration testing.
      detector
    • low Risky intent intent-offensive-security rules/change-management.md:90
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Annual penetration test is expected for SOC 2 and increasingly for ISO
    • low Risky intent intent-offensive-security rules/change-management.md:93
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Bug bounty programs count as continuous security testing
    • low Risky intent intent-offensive-security rules/logging-monitoring.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Minimum logging: authentication events (success + failure), privilege escalation, data access, configuration changes, admin actions
    • low Risky intent intent-offensive-security rules/logging-monitoring.md:55
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Monitoring should cover: failed authentication (brute force), privilege escalation, unusual data access patterns, configuration changes

    Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "catalog_group"
    • note frontmatter-key unknown frontmatter key "catalog_order"

    Process rating: all ten parameters 64/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 69 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3269 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 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

    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +4Description says when NOT to use the skill
    • +3Description length 342: enough signal without eating the budget
    • +4Structure: 23 headings
    • +3Step-by-step instructions: 69 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (9 of 9)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: clean
    This is a markdown-only ISO audit guide with expected evidence-collection steps, but users should handle the collected audit data carefully.
    LLM: benign (high) · VirusTotal: · 29 May 2026