SKILLEMALL.ai
GitHub ↗ RU Sign in

BB cloudflare-agent-tunnel

Give each OpenClaw agent its own secure HTTPS URL using Cloudflare Tunnel (cloudflared). No SSL certificates to manage, no ports to expose publicly. Use when setting up secure cloud access for OpenClaw agents on a VPS, assigning per-agent subdomains (koda.yourdomain.com), enabling HTTPS without nginx or Let's Encrypt, or connecting a custom domain to an agent. Covers named tunnels (permanent URL, free Cloudflare account — preferred), quick tunnels (temporary, no account), multi-agent setup on a single VPS, and custom domain configuration.

ClawHub Agent Skills author: maverick-software v1.1.0 4 files · 1 script body ≈ 1 364 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

ReferenceCloudflareAI and agentstype 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
B
88/100
safety, quality, tests
Safety 60%
92
Quality 40%
83
Run on models
none yet
Process rating
B
66/100
Nearly there
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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
    • medium Exfiltration exfil-webhook-url SKILL.md:150
      Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill)
      # Start quick tunnel — prints a random https://*.trycloudflare.com URL
      security skill
    • low Dangerous commands cmd-background-process references/custom-domains.md:153
      Starts a background / autostarted process (documentation of a security skill)
      systemctl enable cloudflared-koda cloudflared-alex cloudflared-jordan
      security skill
    • low Dangerous commands cmd-background-process scripts/tunnel-setup.sh:115
      Starts a background / autostarted process
      systemctl enable "$SERVICE_NAME"
    • low Dangerous commands cmd-background-process SKILL.md:115
      Starts a background / autostarted process (documentation of a security skill)
      systemctl enable cloudflared-koda
      security skill

    Files scanned: 4. 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 66/100

    • 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. 3 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 7 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1364 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • -2localhost URLs: will not work for another user
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 544: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 7 items
    • +4Has examples (14 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    This skill is coherent and not deceptive, but it can publish an OpenClaw agent interface through a persistent root-run Cloudflare tunnel without clearly requiring access controls.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026