Security audit
Security checks for vulnerabilities and agentic risk
This consumer research skill is mainly a disclosed Chinese-language template and helper script for web-search prompts, local research notes, and report generation, with privacy practices users should tighten before using real survey data.
Before installing, confirm that a Chinese-language consumer research helper is what you want. Use anonymized or aggregated survey data where possible, add your own consent and privacy notice before collecting responses, avoid storing direct identifiers, and keep generated reports and data files inside the intended project directory.
该技能与“消费者调研”主题总体相关，但声明明显高于实际实现。代码的核心能力是：1）为目标人群画像和需求分析生成若干 web_search 查询语句；2）保存外部提供的数据到本地文件；3）根据本地已有 JSON 数据生成格式化报告。它并没有实现声明中的问卷设计、问卷数据处理，也没有真正执行消费者洞察分析或需求挖掘算法，更多是一个搜索提示与结果存储/报告工具。因此描述不能准确代表实际代码能力，属于能力夸大和部分功能缺失的描述不匹配。
The skill declares file-writing behavior via its dependency setup and documented data persistence, but does not define an explicit tool scope such as allowed-tools or permissions. This creates an authorization ambiguity where the runtime may grant broader file access than users expect, increasing the chance of unintended reads/writes in the workspace.
The trigger conditions are broad enough that the skill could be invoked in many loosely related product or research contexts without a clear necessity check. Overbroad invocation increases exposure to data collection, web queries, and persistence of research artifacts when a narrower or less data-invasive skill might have sufficed.
The skill explicitly stores profile, needs-analysis, and questionnaire-result files, but provides only a generic privacy note and does not clearly warn about retention, sensitivity, access boundaries, or deletion. In a consumer research context, saved questionnaire data can contain personal or quasi-identifying information, so unclear persistence creates real privacy and compliance risk.
The questionnaire explicitly collects demographic and economic data such as gender, age, city tier, and monthly income, but provides no notice about purpose, retention, sharing, consent, or respondent rights. In a consumer-research skill, this increases privacy and compliance risk because operators could deploy the template to gather personally sensitive profiling data without informing participants how the data will be used.
The guideline covers participant recruitment, data collection, cleaning, analysis, and inclusion of 'raw data' in an appendix, but it never mentions informed consent, lawful basis, minimization, de-identification, retention limits, or access controls. In a consumer-research skill, this omission can normalize collecting and sharing potentially sensitive participant information in ways that violate privacy expectations or data-protection requirements.
The file-level docstring and all user-facing descriptions are exclusively in Chinese, which imposes a specific language on users. The policy for this category flags language or locale constraints when they are forced without opt-in or justification.
The argparse description, help text, printed status messages, and report headings are all fixed in Chinese with no alternative locale handling. This creates a natural-language policy issue because the skill requires a specific language rather than allowing user choice or documenting a justified regional restriction.
The manifest description and the rest of the skill are written entirely in Chinese, with no indication that users may request another language or locale. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.
All user-facing content in the template is fixed in Chinese, with no indication that respondents can choose another language or that the template is intended only for a Chinese-speaking audience. This creates a natural-language policy concern when a skill forces a specific language without user opt-in or documented locale justification.
The entire skill content is written in Chinese and does not indicate that users may choose another language or that the locale restriction is intentional and justified. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
The manifest states that the skill supports questionnaire design, but this file only generates web-search query instructions, saves data, and produces a report. There is no code for designing questionnaires or survey instruments, creating a mismatch between the claimed capability and the actual implementation in this skill file.
The manifest describes a consumer-research capability focused on audience profiling, needs discovery, questionnaire design, and data processing. In addition to generating search instructions, this file implements local data storage functions and later writes a markdown report to disk, which is broader than a purely analytic/research description and is not mentioned in the manifest.
No suspicious patterns detected.
