Back to skill

Security audit

习惯养成教育追踪系统

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent and local-only, but it can persist and modify sensitive child and family records with overly broad activation and insufficient user confirmation.

Install only if you intentionally want a Chinese-language local tracker for child habit and education records. Before use, require explicit confirmation for every create, update, archive, merge, or delete action, and treat the SQLite database as private family data that may need backups and access controls.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (15)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

声明描述的是一个较完整的家庭教育习惯追踪与分析系统,而这段代码的实际职责非常窄,只是“教育付出”表的写入和读取辅助函数。它访问的是本地 SQLite 数据库,资源类型与声明并不冲突,也没有发现额外的敏感或未声明外部能力;但其主要功能明显小于且不同于声明中的综合追踪、分析、查询系统。尤其是描述强调习惯记录、行为变化、干预效果分析和总结,而代码没有任何分析、统计、过滤、习惯维度建模或干预效果计算逻辑。因此应判定为描述与实际行为存在实质性不匹配。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation scope is broad enough to trigger on ordinary parenting discussions, which can cause the agent to enter a mode that writes to a persistent local database without clear user intent. In this skill's context, over-triggering is riskier because the skill handles sensitive family and child behavioral data and includes modification workflows such as inserts, updates, archiving, and merges.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill description and all operating instructions are written entirely in Chinese and present the skill as operating in that language, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to perform persistent writes, updates, archiving, and deletion/merge operations on a local database, but it provides no user-facing warning, consent, or confirmation requirement. This is dangerous because users may unknowingly create or alter long-lived records about children and family members, and destructive actions like merging or deleting redundant records can silently cause data loss or privacy harm.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file's human-facing docstrings are written only in Chinese, which can constitute a language-policy issue when no user opt-in or locale justification is provided. There is no indication that this skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module and function docstrings use only Chinese ("归档习惯" / "归档一个习惯"), which indicates a fixed language choice in user-facing natural-language text. Under the language/locale policy, this is a violation when no user opt-in or documented locale constraint is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file contains user-facing documentation and output exclusively in Chinese, including the module docstrings and the runtime usage message. This imposes a specific language on users without any opt-in, fallback, or documented region-specific justification, which matches the natural-language locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Docstrings and the script's user-facing context are written in Chinese, which can impose a language requirement without user opt-in. The file does not indicate that the skill is region-specific or provide any mechanism for selecting another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and function docstrings are written only in Chinese, which imposes a language choice in the skill's natural-language surface. The file does not offer an opt-in, alternative locale, or a documented region-specific justification, matching the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

该 markdown 文件全文以中文撰写,标题、字段说明和枚举说明均未提供可选语言或说明其仅适用于特定中文用户群。按照语言/locale 政策,若技能或其关键参考文档默认强制单一语言且没有用户选择或明确的区域性正当说明,可能构成自然语言层面的策略问题。

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This code inserts a new intervention record into a SQLite database and commits the change, which is a persistent file-backed write operation. While the function and docstring describe the purpose in code terms, there is no user-facing confirmation, logging, or warning indicating that running this function will modify local data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This code performs persistent data modifications by updating the habits table and inserting an archive summary into the database, but it provides no confirmation prompt, logging, print statement, or explanatory warning around the write operation. Because this is a code file, safety-relevant writes should have some visible disclosure unless clearly surfaced elsewhere.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module and function docstrings use Chinese exclusively, which may impose a language constraint on users or maintainers without opt-in. The policy requires avoiding forced language or locale unless a choice is offered or the restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This code inserts contributor, description, notes, and timestamps into a persistent SQLite database, which is a file write affecting user data. There is no confirmation prompt, logging, or user-facing disclosure in this file indicating that the data will be stored locally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The script reads from a local SQLite database containing habit records and intervention notes, which are user-related data. Although the functions have internal docstrings, there is no confirmation prompt, user-facing log, or printed disclosure indicating that personal habit data will be accessed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.