SKILLEMALL.ai
GitHub ↗ RU Sign in

FC pachca-bots

Бот или интеграция в Пачке: что выбрать (входящий вебхук, бот с событиями, приложение с авторизацией), создание и настройки бота, токены и права, доступ к чатам, приём событий (подпись, повторы, защита от дублей, история событий), кнопки, формы, разворачивание ссылок, витрина. Когда: «сделать бота», «уведомления из CRM или CI в чат», «входящий вебхук», «исходящий вебхук», «бот команд или уведомлений не получает сообщения», «проверить подпись вебхука», «кнопки в сообщении бота», «форма, модальное окно», «превью ссылок, unfurl», «права токена бота», «токен бота утёк», «опубликовать бота в витрине», "build a Pachca bot", "incoming webhook", "outgoing webhook", "bot gets no events", "verify webhook signature", "message buttons", "modal form", "link unfurling", "reissue a leaked bot token". Not for: an AI agent that answers in threads or does not hear a mention → pachca-ai-agent; an app acting for an employee → pachca-oauth; scripts, pagination, 429 → pachca-api; writing messages yourself → pachca-messaging.

Blockedguard blocked the skill: signs of malicious behaviour
pachca/openapi Agent Skills author: pachca 3 files body ≈ 5 325 tokens Open the sourcegithub.com↗ analyzed 5 h ago

Бот или интеграция в Пачке: что выбрать (входящий вебхук, бот с событиями, приложение с авторизацией), создание и настройки бота, токены и права, доступ к…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
F
39/100
safety, quality, tests
Safety 60%
10
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

The same skill appears in 1 more place: openapi

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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. 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 · 1

  • critical Exfiltration exfil-send-secrets-to-url SKILL.md:99
    Instruction to send secrets/history to an external endpoint
    - Send messages with buttons using the **bot** token: a Data-button click goes only to the bot that sent the message, and only while the bot is in that chat. Clicks need the «Нажатие кнопок» (`button_

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5325 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 57/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 36 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5325 tokens
  • 100Steps. 72 steps
  • 100Failures and branches. 1 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

  • +3Description length 1018: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +5Description quotes 21 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 72 items
  • +4Reference files are cited in the instructions (2 of 2)
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.