SKILLEMALL.ai
GitHub ↗ RU Sign in

CC blacktea

Spending controls for AI agents that pay online via x402. Set limits, require human approval, audit every payment.

Not recommendedcritical or high security findings
ClawHub Hermes author: Nicolas Martin v0.1.0 MIT-0 2 files body ≈ 822 tokens Open the sourceclawhub.ai↗ analyzed 30 h ago

Spending controls for AI agents that pay online via x402.

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
72/100
safety, quality, tests
Safety 60%
71
Quality 40%
74
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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.

Broad scope
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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

  • high Broad scope meta-requests-env-secret SKILL.md:1
    Skill asks the runtime to inject credential env vars into its sandbox: EVM_PRIVATE_KEY (high-value: EVM_PRIVATE_KEY) — verify each one is needed for the stated purpose
    required_environment_variables: EVM_PRIVATE_KEY
Medium and low: 3
  • medium Risky intent intent-wallet-secrets skill-card.md:20
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Risk: The skill can let an agent make real x402 payments using a wallet private key. <br>
  • medium Risky intent intent-wallet-secrets SKILL.md:20
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    description: Wallet private key (0x-prefixed) used to sign x402 USDC payments on Base.
  • low Risky intent intent-wallet-secrets SKILL.md:29
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    prompt: "Enter the wallet private key for agent payments (0x-prefixed)"
    quoted

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

Against the Agent Skills spec

  • warning description-long-hermes description is 114 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "required_environment_variables"

Process rating: all ten parameters 55/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 1 mutating operations with no state check
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. No external tools needed
  • 100Steps. 9 steps
  • 100Execution cost. Instruction body is 822 tokens
  • 100Progress reporting. Reports progress

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)
  • +3Description length 114: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 9 items
  • +4Has examples (3 code blocks)
  • +1License stated

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

External checks

ClawHub: clean
The skill clearly describes a payment-control MCP server, but installing it means trusting an external package with a dedicated wallet key and limited spending authority.
LLM: benign (medium) · VirusTotal: · 28 May 2026