Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Chinese business follow-up helper with templates and a small local script; I found no hidden access, persistence, or data exfiltration.
Installers should treat this as a Chinese-language productivity skill for business follow-up planning. Before using it with real contacts, decide where customer or partner records will be stored and avoid letting broad trigger phrases cause unwanted follow-up reports in unrelated conversations.
The README defines the skill's scope very broadly across sales, investor relations, suppliers, distributors, and any recurring business relationship. Overly broad scope increases the chance of misuse, misrouting, or application in contexts with different privacy and compliance expectations without clear constraints.
The trigger phrase "生成今天的渠道跟进清单" is generic and lacks explicit invocation boundaries, making accidental or context-driven activation more likely. In an agent setting, broad triggers can cause the skill to run when the user did not clearly intend to invoke it, leading to unintended processing or actions based on business relationship data.
The README shows workflows for adding channels and updating follow-up status, but does not disclose that user-provided business contact data may be stored or modified. This creates a transparency and consent gap: users may expose sensitive commercial relationship data or cause unintended state changes without understanding persistence behavior.
The trigger conditions include broad, common phrases such as '忘记跟进' and '跟进计划', plus a scheduled daily check, which can cause the skill to activate in conversations that merely mention follow-up planning rather than explicitly requesting this automation. Unintended activation can lead to confusing behavior, unwanted task generation, or accidental handling of business workflow data in the wrong context.
The entire skill file is written as a Chinese-only template library and provides no indication that users may choose another language or that the Chinese-only constraint is intentional for a region-specific use case. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The skill documentation and all example interactions are presented in Chinese, with no indication that users may opt for another language or locale. Under the policy, forcing a specific language without user opt-in can be a natural-language policy concern unless the locale restriction is justified and documented.
This markdown file presents all instructional content in a single language and does not indicate that the user can choose another language or that the file is intended only for a Chinese-language audience. Under the language/locale policy check, forcing one language without opt-in can be a natural-language policy issue.
This code file contains natural-language strings and comments such as '每日跟进检查脚本' and printed output in Chinese, which effectively forces a specific language for users. The policy allows locale constraints only when the skill offers opt-in or clearly documents a justified region-specific limitation, which is not present here.
No suspicious patterns detected.
