Security audit
Security checks for vulnerabilities and agentic risk
This is a Hebrew-focused prompt-writing skill that does not run code, access data, install anything, or persist changes.
Install this if you want a Hebrew-first assistant for creating polished AI image and video prompts. Be aware that it will answer in Hebrew by default unless you ask for English, but it does not appear to access private data, run commands, or make system changes.
This plain-text skill/example file presents its instructions and request/response scaffolding entirely in Hebrew, which can impose a specific language on users without any stated opt-in or alternative. The policy requires flagging language or locale constraints when they are forced rather than offered as a choice or clearly justified.
The text states 'always in Hebrew by default' and allows English only upon explicit request. This imposes a language policy without offering general user language choice or documenting a justified locale-specific constraint, which matches the natural-language policy violation criteria.
The instruction says to always answer in Hebrew unless the user explicitly asks for English. This imposes a default language policy on users rather than offering a neutral language choice or explicit opt-in, which matches the locale/language policy violation criteria.
No suspicious patterns detected.
