SKILLEMALL.ai
GitHub ↗ RU Sign in

BF api-gateway

API gateway for calling third-party APIs with managed OAuth connections, provided by Maton (https://maton.ai). Use this skill when users want to interact with external services like Slack, HubSpot, Salesforce, Google Workspace, Stripe, and more. Access is scoped to connections you explicitly authorize via OAuth - the API key alone does not grant access to any third-party service. Requires network access and valid Maton API key.

ClawHub Agent Skills author: IceMasterT v1.0.0 80 files body ≈ 6 775 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 36/100 · Will not run — References files that are not bundled: references/pipedrive.md, references/podio.md, references/quickbooks.md

IntegrationSlackSalesforceHubSpotStripeSales and CRMtype 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
80/100
safety, quality, tests
Safety 60%
89
Quality 40%
67
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: references/pipedrive.md, references/podio.md, references/quickbooks.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Obfuscation 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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Obfuscation obf-base64-blob references/google-analytics-data.md:149
    Long base64-looking blob
    - [Run Realtime Report](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/runRealtimeReport)
  • medium Obfuscation obf-base64-blob references/google-analytics-data.md:150
    Long base64-looking blob
    - [Batch Run Reports](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/batchRunReports)
  • low Obfuscation obf-base64-blob SKILL.md:438
    Long base64-looking blob (quoted — discussed, not commanded)
    req = urllib.request.Request('https://gateway.maton.ai/google-sheets/v4/spreadsheets/122B…I4M/values/Sheet1!A1:B2')
    quoted

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6775 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/pipedrive.md
  • warning missing-ref reference to a missing file: references/podio.md
  • warning missing-ref reference to a missing file: references/quickbooks.md
  • warning missing-ref reference to a missing file: references/quo.md
  • warning missing-ref reference to a missing file: references/salesforce.md
  • warning missing-ref reference to a missing file: references/signnow.md
  • warning missing-ref reference to a missing file: references/sendgrid.md
  • warning missing-ref reference to a missing file: references/slack.md
  • warning missing-ref reference to a missing file: references/snapchat.md
  • warning missing-ref reference to a missing file: references/squareup.md
  • warning missing-ref reference to a missing file: references/stripe.md
  • warning missing-ref reference to a missing file: references/systeme.md
  • warning missing-ref reference to a missing file: references/tally.md
  • warning missing-ref reference to a missing file: references/telegram.md
  • warning missing-ref reference to a missing file: references/ticktick.md
  • warning missing-ref reference to a missing file: references/todoist.md
  • warning missing-ref reference to a missing file: references/toggl-track.md
  • warning missing-ref reference to a missing file: references/trello.md
  • warning missing-ref reference to a missing file: references/twilio.md
  • warning missing-ref reference to a missing file: references/typeform.md
  • warning missing-ref reference to a missing file: references/vimeo.md
  • warning missing-ref reference to a missing file: references/whatsapp-business.md
  • warning missing-ref reference to a missing file: references/woocommerce.md
  • warning missing-ref reference to a missing file: references/wordpress.md
  • warning missing-ref reference to a missing file: references/xero.md
  • warning missing-ref reference to a missing file: references/youtube.md
  • warning missing-ref reference to a missing file: references/zoho-bigin.md
  • warning missing-ref reference to a missing file: references/zoho-books.md
  • warning missing-ref reference to a missing file: references/zoho-calendar.md
  • warning missing-ref reference to a missing file: references/zoho-crm.md
  • warning missing-ref reference to a missing file: references/zoho-inventory.md
  • warning missing-ref reference to a missing file: references/zoho-mail.md
  • warning missing-ref reference to a missing file: references/zoho-people.md
  • warning missing-ref reference to a missing file: references/zoho-recruit.md

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: references/pipedrive.md, references/podio.md, references/quickbooks.md
  • 0Tools and files. 34 referenced file(s) missing: references/pipedrive.md, references/podio.md, references/quickbooks.md
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 27 mutating operations with no state check
  • 40Consistency. Frontmatter name (api-gateway) differs from the folder (api-gateway-1-0-31)
  • 70Execution cost. Instruction body is 6775 tokens
  • 100Steps. 134 steps
  • 100Failures and branches. 2 branches, has a failure section
  • low 13 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

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 431: enough signal without eating the budget
  • +4Structure: 31 headings
  • +3Step-by-step instructions: 134 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (76 of 77)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: suspicious
The skill is a legitimate-looking Maton API gateway, but it exposes broad write, delete, admin, email, payment, and webhook powers across many connected services without strong safety scoping or confirmation guidance.
LLM: suspicious (high) · VirusTotal: benign · 27 May 2026