SKILLEMALL.ai
GitHub ↗ RU Sign in

CF api-gateway

Call third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected. Use this skill when the user names a connected app and a concrete action in it - read a mailbox, query a CRM, file an issue, update a spreadsheet, run a query through a connected search or scraping provider. Every call goes to an app the user connected. It is not a general-purpose browser or network client, and it cannot reach a service with no Maton connection. Some connected apps are themselves scraping, browsing, or document-processing services (Firecrawl, Reducto, search providers); using them fetches or processes third-party content on that provider's infrastructure, at the user's explicit request, and is that app's capability rather than this skill's. It also manages event triggers, webhook destinations that forward event payloads to an external URL until deleted, and local `--exec` handlers that run a script per event - separate, high-risk capabilities beyond a normal API call. Default to read and list calls; every write, connection, trigger, destination, or handler needs explicit user confirmation.

ClawHub Agent Skills author: byungkyu v1.2.17 MIT-0 80 files body ≈ 14 045 tokens Open the sourceclawhub.ai↗ analyzed 32 h ago

Call third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected.

As a process F 59/100 · Will not run — References files that are not bundled: references/time/triggers.md, references/instantly/README.md, references/jira/README.md

IntegrationSlackGitHubInfrastructureSoftware developmentData and analyticstype 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
C
62/100
safety, quality, tests
Safety 60%
75
Quality 40%
37
Run on models
51
No improvement model run: 54% with skill · 46% without
Process rating
F
59/100
Will not run
References files that are not bundled: references/time/triggers.md, references/instantly/README.md, references/jira/README.md
Tools and files w 18
0
Inputs and preconditions w 11
0
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.

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.

Broad scope 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 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.

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 13

✓ No critical or high findings

Medium and low: 13
  • medium Obfuscation obf-base64-blob references/google-analytics-data/README.md:172
    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/README.md:173
    Long base64-looking blob
    - [Batch Run Reports](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/batchRunReports)
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Grep Glob
  • low Secrets in code secret-high-entropy-token references/callrail/README.md:34
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "ACC0…cb3",
    quoted
  • low Secrets in code secret-high-entropy-token references/callrail/README.md:73
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "COM0…9e9",
    quoted
  • low Secrets in code secret-high-entropy-token references/callrail/README.md:130
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "CAL0…69b",
    quoted
  • low Secrets in code secret-high-entropy-token references/callrail/README.md:252
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "TRK0…11f",
    quoted
  • low Secrets in code secret-high-entropy-token references/callrail/README.md:261
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "COM0…9e9",
    quoted
  • low Secrets in code secret-high-entropy-token references/fastmail/README.md:228
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "blobId": "G619…1b9",
    quoted
  • low Secrets in code secret-high-entropy-token references/fastmail/README.md:243
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    { "blobId": "G619…1b9", "type": "application/pdf", "name": "report.pdf", "disposition": "attachment" }
    quoted
  • low Secrets in code secret-high-entropy-token references/fathom/README.md:257
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "secret": "whse…row",
    quoted
  • low Secrets in code secret-high-entropy-token references/github/triggers.md:1137
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "node_id": "MDIz…DU3"
    quoted
  • low Secrets in code secret-high-entropy-token references/github/triggers.md:1311
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "node_id": "MDEw…jY5",
    quoted

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

Against the Agent Skills spec

  • error description-long description is 1143 chars, limit 1024
  • warning body-long SKILL.md body ≈ 14045 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/time/triggers.md
  • warning missing-ref reference to a missing file: references/instantly/README.md
  • warning missing-ref reference to a missing file: references/jira/README.md
  • warning missing-ref reference to a missing file: references/jobber/README.md
  • warning missing-ref reference to a missing file: references/jotform/README.md
  • warning missing-ref reference to a missing file: references/kaggle/README.md
  • warning missing-ref reference to a missing file: references/keap/README.md
  • warning missing-ref reference to a missing file: references/kibana/README.md
  • warning missing-ref reference to a missing file: references/kit/README.md
  • warning missing-ref reference to a missing file: references/klaviyo/README.md
  • warning missing-ref reference to a missing file: references/lemlist/README.md
  • warning missing-ref reference to a missing file: references/linear/README.md
  • warning missing-ref reference to a missing file: references/linkedin/README.md
  • warning missing-ref reference to a missing file: references/linkedin-community-management/README.md
  • warning missing-ref reference to a missing file: references/mailchimp/README.md
  • warning missing-ref reference to a missing file: references/mailerlite/README.md
  • warning missing-ref reference to a missing file: references/mailgun/README.md
  • warning missing-ref reference to a missing file: references/make/README.md
  • warning missing-ref reference to a missing file: references/manus/README.md
  • warning missing-ref reference to a missing file: references/manychat/README.md
  • warning missing-ref reference to a missing file: references/memelord/README.md
  • warning missing-ref reference to a missing file: references/microsoft-excel/README.md
  • warning missing-ref reference to a missing file: references/microsoft-teams/README.md
  • warning missing-ref reference to a missing file: references/microsoft-to-do/README.md
  • warning missing-ref reference to a missing file: references/monday/README.md
  • warning missing-ref reference to a missing file: references/motion/README.md
  • warning missing-ref reference to a missing file: references/netlify/README.md
  • warning missing-ref reference to a missing file: references/notion/README.md
  • warning missing-ref reference to a missing file: references/notion-mcp/README.md
  • warning missing-ref reference to a missing file: references/one-drive/README.md
  • warning missing-ref reference to a missing file: references/one-note/README.md
  • warning missing-ref reference to a missing file: references/outlook/README.md
  • warning missing-ref reference to a missing file: references/pdf-co/README.md
  • warning missing-ref reference to a missing file: references/pipedrive/README.md
  • warning missing-ref reference to a missing file: references/podio/README.md
  • warning missing-ref reference to a missing file: references/posthog/README.md
  • warning missing-ref reference to a missing file: references/quickbooks/README.md
  • warning missing-ref reference to a missing file: references/quo/README.md
  • warning missing-ref reference to a missing file: references/reducto/README.md
  • warning missing-ref reference to a missing file: references/resend/README.md
  • warning missing-ref reference to a missing file: references/salesforce/README.md
  • warning missing-ref reference to a missing file: references/sendgrid/README.md
  • warning missing-ref reference to a missing file: references/sentry/README.md
  • warning missing-ref reference to a missing file: references/sharepoint/README.md
  • warning missing-ref reference to a missing file: references/signnow/README.md
  • warning missing-ref reference to a missing file: references/slack/README.md
  • warning missing-ref reference to a missing file: references/snapchat/README.md
  • warning missing-ref reference to a missing file: references/squareup/README.md
  • warning missing-ref reference to a missing file: references/squarespace/README.md
  • warning missing-ref reference to a missing file: references/stripe/README.md
  • warning missing-ref reference to a missing file: references/sunsama-mcp/README.md
  • warning missing-ref reference to a missing file: references/supabase/README.md
  • warning missing-ref reference to a missing file: references/systeme/README.md
  • warning missing-ref reference to a missing file: references/tally/README.md
  • warning missing-ref reference to a missing file: references/tavily/README.md
  • warning missing-ref reference to a missing file: references/telegram/README.md
  • warning missing-ref reference to a missing file: references/ticktick/README.md
  • warning missing-ref reference to a missing file: references/todoist/README.md
  • warning missing-ref reference to a missing file: references/toggl-track/README.md
  • warning missing-ref reference to a missing file: references/trello/README.md
  • warning missing-ref reference to a missing file: references/twenty/README.md
  • warning missing-ref reference to a missing file: references/twilio/README.md
  • warning missing-ref reference to a missing file: references/typeform/README.md
  • warning missing-ref reference to a missing file: references/unbounce/README.md
  • warning missing-ref reference to a missing file: references/vercel/README.md
  • warning missing-ref reference to a missing file: references/vercel-ai-gateway/README.md
  • warning missing-ref reference to a missing file: references/vimeo/README.md
  • warning missing-ref reference to a missing file: references/wati/README.md
  • warning missing-ref reference to a missing file: references/whatsapp-business/README.md
  • warning missing-ref reference to a missing file: references/woocommerce/README.md
  • warning missing-ref reference to a missing file: references/wordpress/README.md
  • warning missing-ref reference to a missing file: references/wrike/README.md
  • warning missing-ref reference to a missing file: references/xero/README.md
  • warning missing-ref reference to a missing file: references/youtube/README.md
  • warning missing-ref reference to a missing file: references/youtube-analytics/README.md
  • warning missing-ref reference to a missing file: references/youtube-reporting/README.md
  • warning missing-ref reference to a missing file: references/zoom/README.md
  • warning missing-ref reference to a missing file: references/zoom-admin/README.md
  • warning missing-ref reference to a missing file: references/zoho-bigin/README.md
  • warning missing-ref reference to a missing file: references/zoho-bookings/README.md
  • warning missing-ref reference to a missing file: references/zoho-books/README.md
  • warning missing-ref reference to a missing file: references/zoho-calendar/README.md
  • warning missing-ref reference to a missing file: references/zoho-crm/README.md
  • warning missing-ref reference to a missing file: references/zoho-inventory/README.md
  • warning missing-ref reference to a missing file: references/zoho-mail/README.md
  • warning missing-ref reference to a missing file: references/zoho-people/README.md
  • warning missing-ref reference to a missing file: references/zoho-projects/README.md
  • warning missing-ref reference to a missing file: references/zoho-recruit/README.md
  • warning missing-ref reference to a missing file: references/{source}/triggers.md

Process rating: all ten parameters 59/100

Will not run. References files that are not bundled: references/time/triggers.md, references/instantly/README.md, references/jira/README.md
  • 0Tools and files. 89 referenced file(s) missing: references/time/triggers.md, references/instantly/README.md, references/jira/README.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 90 mutating operations with no state check
  • 40Execution cost. Instruction body is 14045 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 207 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 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)
  • +3Description length 1142: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 75 headings
  • +3Step-by-step instructions: 207 items
  • +3Output format is stated explicitly
  • +4Has examples (84 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.

Model run · 7 Sept 2026

With the skill
54%
+8 pp vs baseline
Without the skill (baseline)
46%
triggers: +100% / −100%

No improvement Pass rate 54% is below threshold 80% · 7 cases · $0.073

External checks

ClawHub: clean
This is a broad but clearly disclosed API-gateway skill for connected Maton apps; it is not risk-free because it can affect live accounts, but the sensitive capabilities are purpose-aligned and mostly guarded by explicit confirmation instructions.
LLM: benign (medium) · VirusTotal: · 12 Sept 2026