SKILLEMALL.ai
GitHub ↗ RU Sign in

FB x402-compute

This skill should be used when the user asks to "provision GPU instance", "integrate agent pods over an API", "create pods for my customers", "pod webhooks", "pod events", "spin up a cloud server", "list compute plans", "browse GPU pricing", "deploy AI machine", "one-click GPU running an LLM", "deploy a private LLM endpoint", "OpenRouter-ready endpoint", "agent deploy GPU", "spin up my own OpenAI-compatible endpoint", "extend compute instance", "resize compute instance", "destroy server instance", "check instance status", "list my instances", "top up compute credits", "check credit balance", "run inference on the grid", "decentralized inference", "OpenAI-compatible API", "multimodal embeddings", "EmbeddingGemma 2", "embed image", "embed audio", "embed video", "mixed media vectors", "local embeddings", "speech to text", "transcribe audio", "Grid transcription", "Whisper STT", "dictation", "local dictation", "voice engine", "confidential / TEE inference", "list grid models", "check grid capacity", "Laya", "System One", "Jev-compatible decisions", "typed decision model", "private Laya", "serve Laya from the node app", "run a node", "provide compute", "become a grid node", "node operator", "join the grid", "stake to run a node", "serve a model on the grid", "earn from compute", "deploy an always-on AI agent", "deploy a hosted OpenClaw agent", "spin up a ClawPod", "agent pod", "hosted agent with its own wallet", "free agent trial", "deploy a processor", "sell my code per call", "monetize an endpoint", "publish a paid API", "connect a processor as an MCP tool", "back up my agent", "agent backup", "restore my agent", "migrate my agent", "agent vault", "snapshot my agent's memory", "move my agent to a new machine", or manage Singularity Cloud Network compute. Seven jobs: SGL Machines (GPU/VPS provisioning across Vultr & DigitalOcean), AI Machines (one-click GPU running an LLM — deploy a private OpenAI-compatible endpoint, or join the grid & earn), SGL Grid (decentralized co

ClawHub Agent Skills author: Ivaavi.eth v1.32.0 MIT-0 32 files · 17 scripts body ≈ 12 525 tokens Open the sourceclawhub.ai↗ analyzed 8 d ago

This skill should be used when the user asks to "provision GPU instance", "integrate agent pods over an API", "create pods for my customers", "pod webhooks"…

As a process B 72/100 · Nearly there — weak spots: result and completion, execution cost

IntegrationTelegramAI 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
F
22/100
safety, quality, tests
Safety 60%
10
Quality 40%
41
Run on models
none yet
Process rating
B
72/100
Nearly there
Result and completion w 14
0
Execution cost w 6
40
Failures and branches w 10
50
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 30

✓ No critical or high findings

Medium and low: 30
  • medium Exfiltration net-credential-use references/agent-pods-api.md:58
    Credential used in a network call (verify the destination is the intended service)
    curl -s "https://comp….cc/pods/v1/pods/$POD" -H "X-API-Key: $SGL_API_KEY" | jq -r .pod.status
  • medium Exfiltration net-credential-use references/agent-pods-api.md:168
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST ".../pods/v1/pods/$POD/actions" -H "X-API-Key: $KEY" \
  • medium Exfiltration net-credential-use references/agent-pods-api.md:207
    Credential used in a network call (verify the destination is the intended service)
    curl -s "https://comp….cc/pods/v1/events?after=41&limit=50" -H "X-API-Key: $SGL_API_KEY"
  • medium Exfiltration net-credential-use references/agent-pods.md:180
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods       -H "X-API-Key: $COMPUTE_API_KEY"   # list yours
  • medium Exfiltration net-credential-use references/agent-pods.md:181
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods/<id>  -H "X-API-Key: $COMPUTE_API_KEY"   # details + heartbeat + masked creds
  • medium Exfiltration net-credential-use references/agent-pods.md:223
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods/<id>/wallet -H "X-API-Key: $COMPUTE_API_KEY"   # addresses + balances
  • medium Exfiltration net-credential-use references/agent-pods.md:240
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X DELETE https://comp….cc/compute/instances/<pod.id> -H "X-API-Key: $COMPUTE_API_KEY"
  • medium Dangerous commands cmd-pipe-to-shell references/node-operator.md:52
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -sSf https://grid….cc/install.sh | sh
    vendor-host
  • medium Exfiltration exfil-send-secrets-to-url references/processors.md:43
    Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS); the skill's own vendor host)
    Solana keypair. Send it as `X-API-Key` to `https://proc….cc`.
    API authvendor-host
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Edit Bash WebFetch
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:613
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -sSf https://grid….cc/install.sh | sh     # installs `sgl` (Singularity-Layer/sgl-network-node)
    vendor-host
  • medium Exfiltration net-credential-use SKILL.md:732
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods       -H "X-API-Key: $COMPUTE_API_KEY"   # list yours
  • medium Exfiltration net-credential-use SKILL.md:733
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods/<id>  -H "X-API-Key: $COMPUTE_API_KEY"   # details + live heartbeat + masked credential state
  • medium Exfiltration net-credential-use SKILL.md:762
    Credential used in a network call (verify the destination is the intended service)
    curl -s https://comp….cc/pods/<id>/wallet -H "X-API-Key: $COMPUTE_API_KEY"
  • medium Exfiltration net-credential-use SKILL.md:782
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X DELETE https://comp….cc/compute/instances/<pod.id> -H "X-API-Key: $COMPUTE_API_KEY"
  • low Secrets in code secret-password-literal references/multimodal-embeddings.md:33
    Hard-coded password / key literal (may be an example) (placeholder value)
    **Credits auth:** `X-API-Key: x402c_...` with `grid:write`.
    placeholder
  • low Secrets in code secret-high-entropy-token references/node-operator.md:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Token: `$SGL` mint `5c4H…AGS` (Solana). Full model (tiers,
    quoted
  • low Exfiltration net-credential-use references/processors.md:46
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl https://proc….cc/processors -H "X-API-Key: $SGL_API_KEY"
    vendor-host
  • low Secrets in code secret-high-entropy-token references/processors.md:285
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `solana` | USDC (`EPjF…t1v`) | base58 wallet — **the default**, taken from the deploying wallet |
    table
  • low Secrets in code secret-high-entropy-token references/processors.md:286
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `base` | USDC (`0x83…913`) | `0x…` |
    table
  • low Secrets in code secret-high-entropy-token references/processors.md:287
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `robinhood` | USDG (`0x5f…168`) | `0x…` |
    table
  • low Secrets in code secret-high-entropy-token scripts/solana_signing.py:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_MINT_SOLANA = "EPjF…t1v"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/solana_signing.py:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    TOKEN_PROGRAM_ID = "Toke…5DA"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/solana_signing.py:23
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    ATA_PROGRAM_ID = "ATok…knL"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/solana_signing.py:25
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    RENT_SYSVAR_ID = "Sysv…111"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/wallet_signing.py:27
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_ADDRESS = "0x83…913"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/wallet_signing.py:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDG_ADDRESS = "0x5f…168"
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:113
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **$SGL:** native token, live on Solana — mint `5c4H…AGS` (staking secures the grid; see [stak….cc](https://stak….cc))
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:466
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Robinhood Chain also uses an embedded facilitator (no third party). The user signs an off-chain EIP-3009 `TransferWithAuthorization` for USDG (`0x5f…168`, 6 decimals)
    quoted
  • low Exfiltration net-credential-use SKILL.md:561
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl https://grid….cc/v1/models -H "X-API-Key: $COMPUTE_API_KEY"
    vendor-host

Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 3324 chars, limit 1024
  • warning body-long SKILL.md body ≈ 12525 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 3324 of the ~15000-char shared budget for all skills
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 72/100

  • 0Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 12525 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 60 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 3323: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • -31 of 16 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 72 example trigger phrases
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 60 items
  • +4Has examples (24 code blocks)
  • +4Reference files are cited in the instructions (12 of 12)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 41.

External checks

ClawHub: suspicious
This is a legitimate but very powerful cloud, wallet, and hosted-agent management skill whose high-impact operations need careful review before installation.
LLM: suspicious (high) · 10 Oct 2026