SKILLEMALL.ai
GitHub ↗ RU Sign in

FC nevermined-payments

Use when an AI agent must operate on Nevermined autonomously — purchase a payment plan via the x402 protocol (crypto or card), enroll a card and create a spending delegation, obtain a Nevermined API key, register a payment plan or AI agent, or check its credits (as a buyer) or revenue (as a seller) — and when adding x402 payment protection to a TypeScript or Python agent (Express, FastAPI, MCP, Google A2A, Strands, LangChain / LangGraph). Covers the @nevermined-io/payments and payments-py SDKs and the Nevermined REST API.

ClawHub Agent Skills author: nevermined-io v1.0.10 MIT-0 14 files body ≈ 11 539 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Use when an AI agent must operate on Nevermined autonomously — purchase a payment plan via the x402 protocol (crypto or card), enroll a card and create a…

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

ProcedureStripeAI 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
F
34/100
safety, quality, tests
Safety 60%
7
Quality 40%
75
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
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.

How to improve

  1. 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 · 21

✓ No critical or high findings

Medium and low: 21
  • medium Exfiltration net-credential-use references/autonomous-operations.md:49
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" \
  • medium Exfiltration net-credential-use references/autonomous-operations.md:86
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/autonomous-operations.md:122
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/autonomous-operations.md:127
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/autonomous-operations.md:155
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/client-integration.md:22
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/client-integration.md:29
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/customer-onboarding.md:31
    Credential used in a network call (verify the destination is the intended service)
    curl -s -XPOST -H "Authorization: Bearer $ORG_ADMIN_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use references/seller-operations.md:25
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" \
  • medium Exfiltration net-credential-use references/seller-operations.md:41
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" "$B/mrr?asOf=2026…00Z"
  • medium Exfiltration net-credential-use references/seller-operations.md:49
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" "$B/usage?from=...&to=...&limit=50"
  • medium Exfiltration net-credential-use references/seller-operations.md:56
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" "$B/customers?limit=20"
  • medium Exfiltration net-credential-use references/seller-operations.md:72
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $NVM_API_KEY" \
  • medium Exfiltration net-credential-use SKILL.md:116
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $NVM_API_KEY" \
  • medium Exfiltration net-credential-use SKILL.md:133
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use SKILL.md:155
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use SKILL.md:160
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • medium Exfiltration net-credential-use SKILL.md:178
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST -H "Authorization: Bearer $NVM_API_KEY" -H "Content-Type: application/json" \
  • low Secrets in code secret-high-entropy-token references/payment-plans.md:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const USDC_ADDRESS = '0x03…F7e'
    quoted
  • low Secrets in code secret-high-entropy-token references/payment-plans.md:74
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC_ADDRESS = '0x03…F7e'
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:644
    High-entropy token-like string (may be an id, hash or a credential)
    --token-address 0x03…F7e \

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 11539 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "lastUpdated"
  • note edit-residue the text marks something as outdated (lines 381): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 55/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 38 mutating operations with no state check
  • 40Consistency. Frontmatter name (nevermined-payments) differs from the folder (nevermined)
  • 40Execution cost. Instruction body is 11539 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 52 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 23 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

  • +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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 527: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 52 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (12 of 12)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: suspicious
This appears to be legitimate Nevermined payment-integration documentation, but it deserves review because it handles real payment credentials and one manual example can return protected data without explicitly confirming settlement success.
LLM: suspicious (medium) · VirusTotal: · 25 Sept 2026