Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Paperclip Orchestration

v0.1.0

Connect OpenClaw Gateway to Paperclip, diagnose onboarding and reachability failures, claim and store Paperclip API keys, install the Paperclip skill, and or...

0· 106·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ihebsilence/paperclip-orchestration.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Paperclip Orchestration" (ihebsilence/paperclip-orchestration) from ClawHub.
Skill page: https://clawhub.ai/ihebsilence/paperclip-orchestration
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install ihebsilence/paperclip-orchestration

ClawHub CLI

Package manager switcher

npx clawhub@latest install paperclip-orchestration
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name and description claim to connect OpenClaw to Paperclip, perform reachability tests, submit join requests, claim API keys, and operate agents — the SKILL.md contains step-by-step instructions for exactly those tasks, so purpose and capability are aligned.
!
Instruction Scope
The runtime instructions instruct the agent/operator to read the local OpenClaw config (~/.openclaw/openclaw.json -> gateway.auth.token), call Paperclip endpoints, and write a claimed API key file (~/.openclaw/workspace/paperclip-claimed-api-key.json). The skill metadata declares no required config paths or environment variables, so the SKILL.md references files and secrets that were not declared — this mismatch is a scope and transparency concern.
Install Mechanism
This is an instruction-only skill with no install spec and no code files; nothing is written to disk by an installer. That lowers the static install risk.
Credentials
The actions (reading OpenClaw's local gateway token, exercising Paperclip API endpoints, and storing a Paperclip API key) are coherent for the stated purpose. However, the skill asks the operator to persist a sensitive API key to disk and later load PAPERCLIP_API_KEY/PAPERCLIP_API_URL from that file — sensitive operations which should be declared and made explicit in metadata. The metadata currently lists no required credentials or config paths, which is inconsistent with the instructions.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It instructs saving credentials to a user-local path under ~/.openclaw, which is normal for this workflow, but because the skill can be invoked by the agent, confirm that any automatic runs are expected before enabling autonomous invocation.
What to consider before installing
This skill appears to do what it says (onboard OpenClaw to Paperclip), but before installing or allowing autonomous use: 1) Inspect SKILL.md in full and confirm you trust the skill's source — it will read ~/.openclaw/openclaw.json to extract gateway.auth.token and will save a claimed Paperclip API key to ~/.openclaw/workspace/paperclip-claimed-api-key.json. 2) Ensure you are comfortable with an agent reading that local config file and writing credentials to disk; prefer storing secrets in a secure secret store if available. 3) Because the metadata does not declare these config paths or credentials, ask the publisher to explicitly list required config files/env vars (for transparency) or run the steps manually the first time to verify behavior. 4) If you allow autonomous invocation, restrict the agent's network reach and review logs for the join/claim operations. 5) Suggested improvements before trusting the skill: declare required config paths/env vars in metadata, add explicit interactive confirmations before reading/writing secrets, and recommend encrypted storage rather than plaintext files.

Like a lobster shell, security has layers — review code before you run it.

latestvk97ezdwp39xydnq9fp85ymv6kh855gbk
106downloads
0stars
1versions
Updated 1w ago
v0.1.0
MIT-0

Paperclip orchestration

Use this skill to connect an OpenClaw instance to Paperclip and operate it safely afterward.

Keep the workflow strict

  1. Verify which Paperclip base URL is reachable from the current runtime with GET <base-url>/api/health.
  2. Fetch and read the invite-specific onboarding text before submitting anything.
  3. Determine the OpenClaw gateway URL that Paperclip can reach.
  4. Test Paperclip to gateway reachability with the invite's test-resolution endpoint.
  5. Submit the join request with adapterType: "openclaw_gateway" and agentDefaultsPayload.headers["x-openclaw-token"].
  6. If join returns or later triggers pairing required, approve the pending device pairing in OpenClaw and retry.
  7. After board approval, claim the Paperclip API key, save it locally with restrictive permissions, then install any Paperclip skill the onboarding requires.

Do not skip the reachability test. Do not assume a private Docker, LAN, or 172.x address is reachable from Paperclip.

Connectivity checks

Prefer these checks first:

curl -fsS https://paperclip.example.com/api/health
openclaw status
openclaw qr --json
openclaw devices list

Interpretation:

  • openclaw qr --json returns the best advertised gateway URL and the urlSource that produced it.
  • A loopback gateway like ws://127.0.0.1:18789 is not usable from a remote Paperclip deployment.
  • A Tailscale Serve or public HTTPS/WSS URL is usually the right candidate for remote onboarding.
  • Pending pairing requests mean network and auth probably worked far enough to require approval, so stop changing URLs until pairing is handled.

If none of the Paperclip hostnames are reachable, ask the user to add a reachable Paperclip hostname and restart Paperclip before retrying.

Join request requirements

Send a JSON body shaped like this:

{
  "requestType": "agent",
  "agentName": "OpenClaw",
  "adapterType": "openclaw_gateway",
  "capabilities": "OpenClaw gateway agent",
  "agentDefaultsPayload": {
    "url": "wss://your-openclaw-gateway.example",
    "paperclipApiUrl": "https://your-paperclip.example.com",
    "headers": { "x-openclaw-token": "<gateway-token>" },
    "waitTimeoutMs": 120000,
    "sessionKeyStrategy": "issue",
    "role": "operator",
    "scopes": ["operator.admin"]
  }
}

Rules:

  • Read the token from ~/.openclaw/openclaw.json -> gateway.auth.token.
  • Use x-openclaw-token rather than legacy x-openclaw-auth unless compatibility forces otherwise.
  • Keep device auth enabled unless the environment truly cannot pair.
  • Use the working Paperclip base URL for paperclipApiUrl.
  • Preserve trailing slash normalization exactly as the API returns it.

Reachability test

Before the join request, call the invite test endpoint with a URL-encoded gateway URL.

python3 - <<'PY'
import urllib.parse
print(urllib.parse.quote('wss://your-openclaw-gateway.example', safe=''))
PY

Then:

curl -fsS "https://paperclip.example.com/api/invites/INVITE_ID/test-resolution?url=<encoded-url>"

Treat an unreachable result as a real warning. The join request may still be accepted for approval, but the deployment is not fully healthy until Paperclip can resolve the chosen gateway URL.

Approval and claim flow

After the join request succeeds:

  1. Save request id, claimSecret, and claimApiKeyPath.
  2. Wait for board approval.
  3. Claim the API key with the one-time claim secret.
  4. Save the full claim response to ~/.openclaw/workspace/paperclip-claimed-api-key.json.
  5. chmod 600 ~/.openclaw/workspace/paperclip-claimed-api-key.json.
  6. Load PAPERCLIP_API_KEY and PAPERCLIP_API_URL from that file for future runs.

If claim fails before approval, do not rotate secrets or regenerate payloads unnecessarily. Wait for approval and retry once.

Creating and operating agents

First confirm identity and permissions:

curl -sS "$PAPERCLIP_API_URL/api/agents/me" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"

Only proceed with agent creation if the response permits it.

When creating Paperclip agents:

  • Use a valid Paperclip role enum only.
  • Match the role to the work, for example engineer, designer, qa, researcher, pm, or general.
  • Keep prompts and adapter config concise.
  • Reuse the same validated gateway URL and auth header pattern.

Troubleshooting

Invite expired or inactive

Symptom:

{"error":"Invite not found or inactive"}

Action: request a fresh invite.

Join request not yet approved

Symptom:

{"error":"Join request must be approved before key claim"}

Action: wait for Paperclip board approval, then retry the claim once.

Pairing required

Action:

openclaw devices list
openclaw devices approve --latest

Then retry the gateway action that failed.

Remote gateway unreachable from Paperclip

Common causes:

  • loopback or localhost URL
  • non-routable LAN or Docker address
  • Tailscale or reverse proxy hostname not reachable from the Paperclip host
  • wrong scheme, for example testing only wss://... when Paperclip reachability probe expects HTTPS on the same hostname

Action: choose a hostname Paperclip can actually resolve, verify GET /api/health, then rerun the invite test-resolution check.

Invalid role enum

Use only valid Paperclip roles accepted by the target deployment. If the API rejects a custom role, switch to the nearest supported built-in role.

Outcome summary template

When the onboarding or repair work is done, report these exact points:

  • Paperclip base URL used
  • OpenClaw gateway URL used
  • Reachability test result
  • Join request result and request id
  • Claim result
  • Whether the Paperclip skill was installed
  • Remaining blockers, if any

Comments

Loading comments...