Chinese Daily Assistant

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 1:15 AM UTC
• Version: 1.0.1

Overview

This skill is a coherent Chinese-language daily assistant with local static data and no evidence of hidden access, persistence, or malicious behavior.

Safe to install for a Chinese-language daily assistant, with the caveat that the current data is static and may be inaccurate. Review future updates carefully if real weather or exchange APIs are added, because that could introduce network requests and query sharing.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The README presents the skill as specifically for Chinese users and labels the language as Chinese, but does not indicate that other languages are optional or that the user can choose their preferred locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The file frames the skill as “专为中文用户设计” and all examples and interaction patterns assume Chinese-only usage, but it does not state that this locale restriction is optional or justified. This can be a language/locale policy issue because the skill appears to force a specific language context without user opt-in.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger phrases are very broad, natural-language requests such as weather, health advice, and translation prompts, without clear scope or disambiguation boundaries. This can cause over-triggering or unintended invocation of the skill for ordinary conversation, leading to confused routing, unexpected use of external/public data, or accidental handling of requests outside the skill’s intended domain.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The page repeatedly states that the assistant is specifically designed for Chinese users and presents all examples and interface language in Chinese only. Under the language/locale policy, this is a natural-language constraint that should either be optional for users or clearly justified as a region-specific tool.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The description states the skill is designed specifically for Chinese users, which hard-codes a user locale expectation without indicating opt-in or fallback behavior. While not inherently malicious, this can lead to inappropriate activation or exclusion of users whose language preferences do not match, especially when combined with broad multilingual triggers.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger list contains very broad, common terms such as "天气", "翻译", "weather", and "translate" that are likely to appear in ordinary user conversations. This can cause the skill to activate unintentionally, expanding its access and influence beyond user intent and potentially hijacking requests that should be handled by other skills or the base assistant.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The header describes the tool as a Chinese daily-life assistant, and the interface throughout the file is primarily Chinese-oriented. Because the policy scope includes language or locale restrictions, this creates a natural-language policy concern when no user choice or opt-in is provided for language preference.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: This markdown file contains natural-language positioning that limits the skill to Chinese users by default. The policy calls for flagging language or locale constraints when they are forced without user opt-in or an explicit justified regional scope.

Natural-Language Policy Violations

Medium

• Confidence: 89% confidence
• Finding: The promotional language repeatedly states that the skill is optimized and intended for Chinese users, but does not mention any user choice or opt-in for language behavior. This is a natural-language policy concern because it enforces a locale preference without documenting alternatives or justification.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The roadmap explicitly states a future version will connect to real API data, but the accompanying marketing/install content does not disclose that this may introduce network access and transmission of user queries or metadata. That omission can mislead users about privacy and trust boundaries, especially for a currently 'no external API' skill that may later change behavior significantly.

Missing User Warnings

Low

• Confidence: 80% confidence
• Finding: The skill states there is 'no external API dependency' while also saying it uses free public APIs and public data sources, without warning users about freshness, reliability, privacy, or availability implications. This mismatch can mislead users into assuming the skill is fully local or more trustworthy than it is, creating transparency and trust risks rather than direct code-execution danger.

Natural-Language Policy Violations

Low

• Confidence: 84% confidence
• Finding: The file's natural-language strings and comments present the skill strictly as a Chinese-language assistant, including the title '中文日常生活助手' and Chinese-only test labels. Under the policy rule, language-specific behavior should either offer user opt-in or clearly document why the locale restriction is required.

Natural-Language Policy Violations

Low

• Confidence: 92% confidence
• Finding: The title explicitly defines the skill as a Chinese daily-life assistant, and the examples and command phrases throughout the file are exclusively in Chinese. This indicates a fixed language/locale behavior without any documented user choice, which matches the language-policy concern for natural-language policy violations.

Static analysis

No suspicious patterns detected.