Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-writing skill for GPT image generation, and its files are coherent with that purpose without hidden execution or data access.
Installers should expect Chinese-language guidance and mostly English generated image prompts unless they ask for another language. No hidden code execution, credential use, persistence, or broad local access was found.
The trigger says the skill enters professional mode whenever the user 'clearly describes their needs,' but it does not define what counts as clear versus unclear. This creates an ambiguous boundary between professional mode and guided mode, which could lead to unintended invocation of the wrong interaction pattern.
The phrase 'trigger when user needs are vague' is subjective and does not specify how vagueness is determined. Without explicit thresholds, examples, or negative examples, the skill may inconsistently choose guided mode for ordinary requests.
The instruction states that Chinese requests default to English prompts except for Chinese-specific content, which imposes a language choice on the user. This is a natural-language policy concern because it does not offer the user a language preference or opt-in before switching output language.
The natural-language content begins with a Chinese-only description ('所有版本变更记录。') and the entire changelog is written exclusively in Chinese, which can indicate a fixed language/locale assumption. Under the policy, locale-specific language is only acceptable when users are given a choice or the constraint is clearly documented and justified, neither of which appears here.
This markdown file presents all user-facing guidance and templates exclusively in Chinese, including the invocation guidance and response template. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue unless the constraint is explicitly justified, which is not present here.
The entire guide is written in Chinese and provides no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.
The document title and introductory guidance are entirely in Chinese, while the file provides no indication that users may choose another language or locale. Under the policy, a skill that imposes a fixed language without opt-in can be a natural-language policy violation.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
[角色基础] + [种族/职业] + [体型] + [服装装备] + [武器] + [发型] + [面部] + [姿态] + [背景] + [光线] + [渲染风格] + [比例] + [参数]
**示例**:
Fantasy warrior female, human with battle-worn steel armor, athletic build, myth rune engravings glowing on breastplate, worn crimson cape, dual-wielding curved swords in combat stance, long wavy auburn hair, fierce expression with battle scars, standing on cliff edge overlooking dark fantasy forest, dramatic backlight with volumetric god rays, cool blue ambient, digital concept art style, clean lineart with detailed render, 16:9 widescreen, highly detailed textures, portfolio-quality
### 动漫角色
[风格定位] + [角色类型] + [外貌] + [服装] + [标志性元素] + [表情] + [姿态] + [场景] + [画风] + [比例]
**示例**:
Anime cel-shaded character, strong female lead archetype, medium long silver hair with twin tails, bright crimson eyes, school uniform with
该速查表从标题到各节说明均强制采用中文表述，且未见任何提示说明可切换其他语言或该文档仅面向中文用户。按规则，若技能在自然语言层面默认强制特定语言而未提供用户选择，可构成语言/locale 策略问题。
This markdown file contains user-facing instructional content predominantly in Chinese, beginning at L001 and continuing throughout, but it does not indicate that users may choose another language. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.