DD skill-smartcaptcha
Интеграция и администрирование Yandex SmartCaptcha: виджет на сайте (обычный, расширенный, невидимая капча), серверная проверка токена через /validate, React (@yandex/smart-captcha), мобильные приложения (Android/iOS/Flutter через WebView), создание и настройка капчи в Yandex Cloud (консоль, CLI, Terraform, REST/gRPC API), диагностика и тарификация. Используй этот скилл всегда, когда упоминаются SmartCaptcha, «умная капча», «смарткапча», капча Яндекса, smart-token, smartcaptcha.yandexcloud.net, yandex_smartcaptcha_captcha, защита форм/логина/регистрации от ботов и спама в Yandex Cloud, стоимость или квоты SmartCaptcha, а также когда капча Яндекса не отображается или пропускает ботов — даже если слово «капча» не прозвучало, но нужна антибот-защита веб-формы или мобильного приложения.
Интеграция и администрирование Yandex SmartCaptcha: виджет на сайте (обычный, расширенный, невидимая капча), серверная проверка токена через /validate, React…
As a process D 43/100 · Unfinished process — References files that are not bundled: templates/validate.php, templates/validate-amphp.php, templates/mock-validate.php
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.
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".
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
- 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
-
high Exfiltration
exfil-send-secrets-to-urldocs/mobile-webview.md:12Instruction to send secrets/history to an external endpoint (the skill's own vendor host)4. Приложение отправляет токен на **свой бэкенд**, который проверяет его POST-запросом на `https://smartcaptcha.yandexcloud.net/validate` (см. [server-validation.md](server-validation.md)). Ключ серве
vendor-host -
high Exfiltration
exfil-send-secrets-to-urlworkflows/integrate-mobile.md:39Instruction to send secrets/history to an external endpoint (the skill's own vendor host)Приложение отправляет токен на твой API; бэкенд делает POST `https://smartcaptcha.yandexcloud.net/validate` (`x-www-form-urlencoded`: `secret`, `token`, `ip`) и решает по полю `status` (`ok`/`failed`)
vendor-host
Files scanned: 47. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: templates/validate.php - warning
missing-refreference to a missing file: templates/validate-amphp.php - warning
missing-refreference to a missing file: templates/mock-validate.php
Process rating: all ten parameters 43/100
- 0Tools and files. 3 referenced file(s) missing: templates/validate.php, templates/validate-amphp.php, templates/mock-validate.php
- 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. 2 mutating operations with no state check
- 100Steps. 31 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3293 tokens
- medium 15 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +5Description quotes 2 example trigger phrases
- +3Description length 793: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 31 items
- +4Reference files are cited in the instructions (21 of 21)
- +3All 1 scripts are documented
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.