T08 · Insecure Dependencies
Warning
- Location
Skills.md:27- Finding
Unpinned Third-Party Package Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
通勤生存指南
Security checks for vulnerabilities and agentic risk
Overview
This commute skill is not malicious, but it should be reviewed because it stores precise commute history by default.
Install only if you are comfortable with Amap receiving route-query data and with a local `commute_log.json` accumulating detailed commute history. Before regular use, make logging opt-in, store less precise data, set a retention period, protect or delete the log, and pin the `qrcode` dependency.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (3)
T09 · Insecure Skill Coding Practices
Warning
- Location
Skills.md:429- Finding
Query-Parameter Injection in Generated Navigation URLs
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Warning
- Location
Skills.md:458- Finding
Plaintext Persistence of Precise Commute History
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (5)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
文档以“你是一个智能通勤决策助手”并全程规定中文交互示例和中文输出，没有说明可根据用户偏好切换语言，也未提供语言选择。对于通用技能，这构成了语言/locale 约束但缺乏用户显式选择，属于自然语言政策风险。
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
该 markdown 文件将技能触发方式描述为“直接用自然语言告诉我你的通勤信息”，并给出“今天怎么去上班？”这类高频日常表达作为示例，但没有明确限定触发边界、上下文约束或排除条件。这种表述容易与普通聊天请求重叠，增加非预期调用该技能的风险。
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill states that each commute query is saved to a local file for monthly reporting, but the user-facing flow does not prominently obtain consent or clearly warn that detailed travel history will be retained. Persistent storage of home/work locations, times, routes, and habits can reveal sensitive behavioral patterns if the host environment is shared or compromised.
- Content
Ssd 3
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly instructs persistent logging of user commute inputs and derived history in natural language, including addresses, coordinates, times, route choices, and contextual conditions. This creates a sensitive location-history dataset that can expose home/work relationships and daily routines, increasing privacy and stalking risk if accessed by other local users, malware, or backup/sync systems.
- Content
Ssd 3
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The monthly report capability depends on accumulating detailed historical commute records over time, which materially increases sensitivity compared with one-off route queries. Longitudinal data enables inference of routines, absences, work schedules, and frequently visited places, making the skill more dangerous in contexts where devices are shared or logs are backed up externally.
- Content
Static analysis
No suspicious patterns detected.