SKILLEMALL.ai
GitHub ↗ RU Sign in

FF agentpay-sdk

Install and operate the AgentPay SDK. Trigger this when an agent needs to install `agentpay`, explain AgentPay SDK capabilities without probing the machine first, set up or reuse a wallet, check funding, generate funding instructions or a QR, guide the user through policy changes in the TUI or exact admin CLI when explicitly requested, route manual approvals to the local admin approval commands, execute transfers, approvals, or broadcasts using the current CLI behavior instead of stale examples, or use supported plugin-backed merchant payment flows when explicitly relevant.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: wlfi-dev1 v0.3.1 MIT-0 14 files body ≈ 3 685 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 52/100 · Will not run — References files that are not bundled: references/demo-walkthrough.md

IntegrationAI 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
34/100
safety, quality, tests
Safety 60%
7
Quality 40%
74
Run on models
none yet
Process rating
F
52/100
Will not run
References files that are not bundled: references/demo-walkthrough.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The text references files that are not there: add them or drop the references.
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 · 18

  • high Dangerous commands cmd-pipe-to-shell references/install-and-workflows.md:8
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://wlfi.sh | bash
  • high Dangerous commands cmd-pipe-to-shell references/install-and-workflows.md:28
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://wlfi.sh | bash -s -- --skills-only
  • high Dangerous commands cmd-pipe-to-shell references/install-and-workflows.md:86
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://wlfi.sh | bash
Medium and low: 15
  • medium Dangerous commands cmd-pipe-to-shell references/capabilities.md:5
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - One-click bootstrap: `curl -fsSL https://wlfi.sh | bash`
    quoted
  • medium Dangerous commands cmd-pipe-to-shell references/capabilities.md:6
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - One-click skills only: `curl -fsSL https://wlfi.sh | bash -s -- --skills-only`
    quoted
  • medium Dangerous commands cmd-pipe-to-shell references/capabilities.md:7
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - One-click update: rerun `curl -fsSL https://wlfi.sh | bash`
    quoted
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:34
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)
    - One-click bootstrap: `curl -fsSL https://wlfi.sh | bash`
    detector
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:35
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - One-click skills only: `curl -fsSL https://wlfi.sh | bash -s -- --skills-only`
    quoted
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:36
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    - One-click update: rerun `curl -fsSL https://wlfi.sh | bash`
    quoted
  • low Secrets in code secret-high-entropy-token references/capabilities.md:83
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - default payment asset when unspecified: `usd1` on `bsc` -> `0x8d…B0d`
    quoted
  • low Secrets in code secret-high-entropy-token references/install-and-workflows.md:103
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - token address: `0x8d…B0d`
    quoted
  • low Secrets in code secret-high-entropy-token references/install-and-workflows.md:306
    High-entropy token-like string (may be an id, hash or a credential)
    --address 0x8d…B0d \
  • low Secrets in code secret-high-entropy-token references/install-and-workflows.md:334
    High-entropy token-like string (may be an id, hash or a credential)
    --token 0x8d…B0d \
  • low Secrets in code secret-high-entropy-token references/install-and-workflows.md:383
    High-entropy token-like string (may be an id, hash or a credential)
    --token 0x8d…B0d \
  • low Secrets in code secret-high-entropy-token references/install-and-workflows.md:394
    High-entropy token-like string (may be an id, hash or a credential)
    --token 0x8d…B0d \
  • low Exfiltration net-credential-use scripts/prepare-funding-request.mjs:162
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    ? `Please fund ${address} on ${networkLabel} with at least ${formatNativeAmount(amountWei)} ${tokenSymbol}, then tell me once the transfer is confirmed.`
    quoted
  • low Exfiltration net-credential-use scripts/prepare-funding-request.mjs:163
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    : `Please fund ${address} on ${networkLabel} with native ${tokenSymbol} for gas, then tell me once the transfer is confirmed.`,
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:64
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - Default USD1 contract on BSC: `0x8d…B0d`
    quoted

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/demo-walkthrough.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: references/demo-walkthrough.md
  • 0Tools and files. 1 referenced file(s) missing: references/demo-walkthrough.md
  • 0Result and completion. Does not say what the result is
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 9 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 149 steps
  • 100Failures and branches. 16 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3685 tokens
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (30 tags): a typed call is more reliable

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
  • +4No input/output examples
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 580: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 149 items
  • +4Reference files are cited in the instructions (1 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
This AgentPay skill is coherent for wallet payments, but it needs Review because it can install persistent payment tooling, move crypto funds, and uses under-scoped install and payment defaults.
LLM: suspicious (high) · VirusTotal: · 29 May 2026