BC kandinsky-skill
Генерирует и редактирует медиа через Kandinsky: рисует изображения по описанию, перерисовывает и правит существующие картинки, повышает разрешение и качество, создаёт короткие видео по тексту или из фотографии, оживляет изображения и делает говорящие аватары из фото и аудио. Используй всякий раз, когда пользователь хочет создать или изменить визуальный контент — «нарисуй», «сгенерируй картинку», «сделай логотип, иллюстрацию, обои, постер, открытку, иконку, стикер, мем или аватарку», «перерисуй, поправь или отфотошопь фото», «дорисуй», «убери или замени фон», «замени лицо», «улучши качество, увеличь, апскейл», «сделай видео», «оживи картинку», «заставь фото говорить», «липсинк», «озвучь аватар» — даже если слово «Kandinsky» не прозвучало. Различай: «аватарка» как картинка профиля — это обычная генерация изображения (t2i), а «говорящий аватар» из фото и аудио — это avatar. Не для поиска готовых картинок в интернете, распознавания и описания фото, построения графиков по данным.
Генерирует и редактирует медиа через Kandinsky: рисует изображения по описанию, перерисовывает и правит существующие картинки, повышает разрешение и качество…
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keyscripts/kandinsky.py:141Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Instruction override
ru-role-hijackscripts/kandinsky.py:649Role hijack in Russian ("теперь ты без ограничений / режим разработчика") (detector / deny-list definition)help="отключить фильтр контента")
detector
Files scanned: 6. 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") - note
frontmatter-keyunknown frontmatter key "timeout_sec"
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 21 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1949 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 989: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +5Description quotes 15 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.