Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese-focused habit-building helper with no evidence of hidden access, persistence, network use, credential handling, or destructive behavior.
Install this only if you are comfortable with a mostly Chinese, prototype-style habit tracker. Treat its motivation and progress analysis as generic coaching output rather than medical, mental-health, or scientifically validated advice.
The trigger phrase "建立新习惯" is broad, everyday language that can match normal wellness conversations rather than an explicit skill invocation. This increases the chance of unintended activation, causing the skill to intercept user input in contexts where the user did not intend to engage habit-building logic.
The phrase "习惯跟踪" is ambiguous and lacks sufficient context to distinguish a deliberate skill invocation from casual discussion about tracking habits. In an agent environment, such ambiguity can lead to accidental routing or invocation of the skill, which is a security and safety boundary issue.
The trigger "查看习惯进度" is common natural language and does not establish clear invocation boundaries. Because the skill handles personal health-related habit workflows, unintended activation could expose or manipulate progress-related interactions when the user was only speaking generally.
The phrase "我在 [习惯] 上遇到困难" is highly conversational and can overlap with ordinary distress or support-seeking statements. In this health/wellness context, accidental invocation is more concerning because users may be discussing sensitive motivation, mental state, or health struggles rather than intentionally engaging the skill.
The function docstring and surrounding user-facing descriptions are entirely in Chinese, and the skill logic also depends on Chinese-language input tokens such as past failure reasons and habit names. There is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-only regional context, which creates a language/locale policy concern.
This code's user-facing descriptions, docstrings, and generated task text are predominantly in Chinese, which imposes a language choice on downstream users. The file does not indicate that Chinese is optional, configurable, or required for a region-specific purpose, so it creates a natural-language locale policy concern.
This code’s natural-language interface elements and docstrings are presented in Chinese, including the skill title and function documentation, with no indication that language choice is configurable or that the skill is region-specific. That can violate a language/locale policy requiring user choice or explicit justification for non-default language behavior.
This code returns user-facing messages exclusively in Chinese and maps phase names only to Chinese labels. The policy allows locale constraints only when the user is given a language choice or the restriction is clearly documented and justified, neither of which appears in this file.
This Python file contains hard-coded user-facing output entirely in Chinese, including error messages and response content. Because the skill does not offer any language or locale selection, it imposes a specific language on users, which matches the policy's language/locale violation criteria.
The manifest says the skill analyzes user motivation, and the file even imports analyze_motivation at L014, but _handle_motivate returns a fixed canned analysis without using the request data or calling the analyzer. This is not merely incomplete documentation: the code structure implies real analysis capability while the implementation provides fabricated output.
This Python file contains user-facing natural-language strings almost entirely in Chinese, including the title and all printed test output, with no indication that users can select another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The manifest description is entirely in Chinese, which imposes a specific language presentation without any indication that users can choose another language or have opted into this locale. This matches the policy category for language or locale constraints expressed in natural language.
The module header presents the skill description in English and Chinese, and many inline comments are Chinese-only. Under the language/locale policy, natural-language constraints should either offer user choice or be clearly justified as region-specific; this file provides no such justification or opt-in.
No suspicious patterns detected.
