SKILLEMALL.ai
GitHub ↗ RU Sign in

BC stipend

A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account, no API key, no human needed to install or to be paid.

ClawHub Agent Skills author: Graphiker-Australia v1.0.1 MIT-0 2 files body ≈ 9 485 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt.

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

IntegrationAI and agentsSoftware developmenttype 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
75/100
safety, quality, tests
Safety 60%
84
Quality 40%
62
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

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.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:37
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -sL https://stipend.sh/install | sh
    vendor-host
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:95
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -sL https://stipend.sh/install | sh
    vendor-host
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:251
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    >     curl -sL https://stipend.sh/install | sh
    vendor-host
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:107
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; the skill's own vendor host)
    | Shell, and it runs where your files are | `curl -sL https://stipend.sh/install \| sh` |
    tablevendor-host

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 9485 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Execution cost. Instruction body is 9485 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 100Steps. 29 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 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
  • +2Single-language instructions
  • +3Description length 316: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 29 items
  • +4Has examples (29 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
This is a real-money agent wallet that is mostly disclosed, but it encourages self-installation and limited spending through unverified remote code with weak upfront human consent.
LLM: suspicious (high) · 17 Aug 2026