SKILLEMALL.ai
GitHub ↗ RU Sign in

AC ai-security-audit

Perform a security audit on exposed AI service endpoints using OpenClaw threat intelligence. Trigger when the user says "security audit", "audit my AI service", "check my endpoint", "AI endpoint security", "open-webui security", "check if my IP is exposed", "安全审计", "检查我的端点", "AI服务安全加固", or asks about port 18789 exposure.

ClawHub Agent Skills author: yun520-1 v0.1.1 MIT-0 3 files body ≈ 2 836 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 57/100 · 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
92/100
safety, quality, tests
Safety 60%
96
Quality 40%
87
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: ai-security-audit (ClawHub)

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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Dangerous commands cmd-background-process SKILL.md:271
      Starts a background / autostarted process (documentation of a security skill)
      sudo systemctl enable --now auditd
      security skill
    • low Dangerous commands cmd-cron-mention SKILL.md:279
      Mentions editing / listing crontab (documentation of a security skill)
      crontab -l && sudo crontab -l && cat /etc/cron*/*
      security skill
    • low Dangerous commands cmd-privilege SKILL.md:290
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo cp /etc/fail2ban/jail.conf /etc/fail2ban/jail.local
      security skill
    • low Dangerous commands cmd-background-process SKILL.md:292
      Starts a background / autostarted process (documentation of a security skill)
      sudo systemctl enable --now fail2ban
      security skill

    Files scanned: 3. 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 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 35 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2836 tokens
    • 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +3Description length 322: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 35 items
    • +4Has examples (17 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This is a markdown-only AI endpoint security audit guide whose sensitive questions and remediation commands fit its stated purpose.
    LLM: benign (high) · VirusTotal: · 19 Jun 2026