SKILLEMALL.ai
GitHub ↗ RU Sign in

FB api

Integrates and debugs third-party REST and GraphQL APIs: auth, rate limits, pagination, webhooks, with reference for 147 services. Use when calling Stripe, OpenAI, GitHub, Slack, Twilio, or any external service, when a request that should work returns 401, 403, or 429, times out, hits a CORS error, or silently returns wrong data, when choosing an OAuth flow, signing requests, adding retries with backoff and idempotency keys, verifying webhook signatures, consuming SSE streams, uploading files, polling async jobs, caching with ETags, or syncing API data into a local database — with per-service gotchas and curl examples. Not for designing or building your own API.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Iván v1.3.7 MIT-0 37 files body ≈ 3 698 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, progress reporting

IntegrationSlackGitHubStripeSoftware developmentInfrastructureAI and agentstype 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
35/100
safety, quality, tests
Safety 60%
0
Quality 40%
88
Run on models
none yet
Process rating
B
68/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
50
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.

Exfiltration
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. 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.
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 · 51

  • high Exfiltration exfil-webhook-url apis/communication.md:720
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    https://api.telegram.org/bot{TOKEN}
Medium and low: 50
  • medium Exfiltration net-credential-use apis/communication.md:672
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST "https://discord.com/api/webhooks/$WEBHOOK_ID/$WEBHOOK_TOKEN" \
  • medium Exfiltration net-credential-use apis/communication.md:725
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  • medium Exfiltration net-credential-use apis/communication.md:732
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  • medium Exfiltration net-credential-use apis/communication.md:743
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendPhoto" \
  • medium Exfiltration net-credential-use apis/communication.md:751
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/getUpdates?offset=0&limit=10"
  • medium Exfiltration exfil-secret-in-url apis/crm.md:238
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    curl "https://api.pipedrive.com/v1/deals?api_token=…"
    quoted
  • medium Exfiltration net-credential-use apis/crm.md:238
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.pipedrive.com/v1/deals?api_token=…"
  • medium Exfiltration exfil-secret-in-url apis/crm.md:249
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    curl "https://api.pipedrive.com/v1/deals?api_token=…&status=open&limit=50"
    quoted
  • medium Exfiltration net-credential-use apis/crm.md:249
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.pipedrive.com/v1/deals?api_token=…&status=open&limit=50"
  • medium Exfiltration exfil-secret-in-url apis/crm.md:254
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    curl -X POST "https://api.pipedrive.com/v1/deals?api_token=…" \
    quoted
  • medium Exfiltration net-credential-use apis/crm.md:254
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST "https://api.pipedrive.com/v1/deals?api_token=…" \
  • medium Exfiltration exfil-secret-in-url apis/crm.md:267
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    curl "https://api.pipedrive.com/v1/persons/123?api_token=…"
    quoted
  • medium Exfiltration net-credential-use apis/crm.md:267
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.pipedrive.com/v1/persons/123?api_token=…"
  • medium Exfiltration exfil-secret-in-url apis/crm.md:272
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
    curl -X POST "https://api.pipedrive.com/v1/activities?api_token=…" \
    quoted
  • medium Exfiltration net-credential-use apis/crm.md:272
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST "https://api.pipedrive.com/v1/activities?api_token=…" \
  • medium Exfiltration net-credential-use apis/database.md:453
    Credential used in a network call (verify the destination is the intended service)
    curl --digest -u "$ATLAS_PUBLIC_KEY:$ATLAS_PRIVATE_KEY" \
  • medium Exfiltration net-credential-use apis/database.md:461
    Credential used in a network call (verify the destination is the intended service)
    curl --digest -u "$ATLAS_PUBLIC_KEY:$ATLAS_PRIVATE_KEY" \
  • medium Exfiltration net-credential-use apis/productivity.md:869
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.trello.com/1/members/me?key=…&token=…"
  • medium Exfiltration net-credential-use apis/productivity.md:886
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.trello.com/1/boards/$BOARD_ID?key=…&token=…"
  • medium Exfiltration net-credential-use apis/productivity.md:891
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.trello.com/1/boards/$BOARD_ID/lists?key=…&token=…"
  • medium Exfiltration net-credential-use apis/productivity.md:896
    Credential used in a network call (verify the destination is the intended service)
    curl "https://api.trello.com/1/boards/$BOARD_ID/cards?key=…&token=…"
  • medium Exfiltration net-credential-use apis/productivity.md:901
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST "https://api.trello.com/1/cards?key=…&token=…" \
  • low Exfiltration exfil-secret-in-url apis/auth-providers.md:363
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    https://test.stytch.com/v1/public/oauth/google/start?public_token=…
    placeholder
  • low Exfiltration exfil-webhook-url apis/communication.md:672
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -X POST "https://discord.com/api/webhooks/$WEBHOOK_ID/$WEBHOOK_TOKEN" \
    placeholder
  • low Exfiltration exfil-webhook-url apis/communication.md:725
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
    placeholder
  • low Exfiltration exfil-webhook-url apis/communication.md:732
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
    placeholder
  • low Exfiltration exfil-webhook-url apis/communication.md:743
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendPhoto" \
    placeholder
  • low Exfiltration exfil-secret-in-url apis/database.md:206
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…"
    placeholder
  • low Exfiltration net-credential-use apis/database.md:206
    Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable)
    curl "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…"
    variable host
  • low Exfiltration exfil-secret-in-url apis/database.md:211
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl -X PUT "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…" \
    placeholder
  • low Exfiltration net-credential-use apis/database.md:211
    Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable)
    curl -X PUT "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…" \
    variable host
  • low Exfiltration exfil-secret-in-url apis/database.md:217
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl -X PATCH "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…" \
    placeholder
  • low Exfiltration net-credential-use apis/database.md:217
    Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable)
    curl -X PATCH "https://$PROJECT_ID.firebaseio.com/users/user123.json?auth=…" \
    variable host
  • low Exfiltration exfil-secret-in-url apis/media.md:614
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    curl "https://www.googleapis.com/youtube/v3/videos?id=…&part=…&key=…"
    known servicequoted
  • low Exfiltration net-credential-use apis/media.md:614
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    curl "https://www.googleapis.com/youtube/v3/videos?id=…&part=…&key=…"
    known service
  • low Exfiltration exfil-secret-in-url apis/media.md:631
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    curl "https://www.googleapis.com/youtube/v3/videos?id=…&part=…&key=…"
    known servicequoted
  • low Exfiltration net-credential-use apis/media.md:631
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    curl "https://www.googleapis.com/youtube/v3/videos?id=…&part=…&key=…"
    known service
  • low Exfiltration exfil-secret-in-url apis/media.md:636
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    curl "https://www.googleapis.com/youtube/v3/search?q=cats&type=video&maxResults=10&key=…"
    known servicequoted
  • low Exfiltration net-credential-use apis/media.md:636
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    curl "https://www.googleapis.com/youtube/v3/search?q=cats&type=video&maxResults=10&key=…"
    known service
  • low Exfiltration exfil-secret-in-url apis/media.md:641
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    curl "https://www.googleapis.com/youtube/v3/channels?id=…&part=…&key=…"
    known servicequoted
  • low Exfiltration net-credential-use apis/media.md:641
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    curl "https://www.googleapis.com/youtube/v3/channels?id=…&part=…&key=…"
    known service
  • low Exfiltration exfil-secret-in-url apis/media.md:646
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    curl "https://www.googleapis.com/youtube/v3/playlistItems?playlistId=…&part=…&maxResults=50&key=…"
    known servicequoted
  • low Exfiltration net-credential-use apis/media.md:646
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    curl "https://www.googleapis.com/youtube/v3/playlistItems?playlistId=…&part=…&maxResults=50&key=…"
    known service
  • low Exfiltration exfil-secret-in-url apis/productivity.md:869
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl "https://api.trello.com/1/members/me?key=…&token=…"
    placeholder
  • low Exfiltration exfil-secret-in-url apis/productivity.md:886
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl "https://api.trello.com/1/boards/$BOARD_ID?key=…&token=…"
    placeholder
  • low Exfiltration exfil-secret-in-url apis/productivity.md:891
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl "https://api.trello.com/1/boards/$BOARD_ID/lists?key=…&token=…"
    placeholder
  • low Exfiltration exfil-secret-in-url apis/productivity.md:896
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl "https://api.trello.com/1/boards/$BOARD_ID/cards?key=…&token=…"
    placeholder
  • low Exfiltration exfil-secret-in-url apis/productivity.md:901
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl -X POST "https://api.trello.com/1/cards?key=…&token=…" \
    placeholder
  • low Exfiltration net-credential-use credentials.md:45
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl https://api.stripe.com/v1/charges -H "Authorization: Bearer $API_KEY"
    vendor-host
  • low Exfiltration net-credential-use credentials.md:48
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl https://api.stripe.com/v1/charges -H "Authorization: Bearer $STRIPE_PROD_API_KEY"
    vendor-host

Files scanned: 37. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 68/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 40 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3698 tokens
  • 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 13 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
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 670: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 40 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

External checks

ClawHub: suspicious
This API reference skill is not malware, but it needs Review because it persists inferred API context and includes copyable examples that can expose credentials or trigger financial or public side effects if used live.
LLM: suspicious (high) · VirusTotal: · 10 Sept 2026