External Script Fetching
High
- Category
- Supply Chain
- Confidence
- 90% confidence
- Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
- Content
md emoji: "📱" requires: bins: - curl - python3 ---
Security audit
China Phone
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward Chinese phone-number region and carrier lookup, with the main privacy consideration that queried numbers are sent to named public lookup services.
Install only if you are comfortable sending queried Chinese phone numbers to the listed public 360 and Taobao lookup services. Avoid using it for numbers you do not have permission to check, and use the offline prefix fallback when you do not want an external lookup.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)
External Script Fetching
High
- Category
- Supply Chain
- Confidence
- 90% confidence
- Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
- Content
md emoji: "📱" requires: bins: - curl - python3 ---
External Script Fetching
High
- Category
- Supply Chain
- Confidence
- 90% confidence
- Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
- Content
示例：
bash curl -s "https://cx.shouji.360.cn/phonearea.php?number=13812345678" | python3 -c ' import sys, json obj = json.load(sys.stdin) data = obj.get("data") or {}
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill sends phone numbers to third-party public services but does not clearly warn users before doing so. Phone numbers are personal data, so silent transmission to external endpoints creates a privacy and consent risk even if the endpoints are legitimate.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The trigger examples are broad enough that the skill may activate on ordinary discussion about phone numbers or carriers, causing unintended handling of user phone numbers. In this skill, accidental activation matters because the workflow sends numbers to external public endpoints, creating avoidable privacy exposure.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The instruction "始终输出自然中文" forces a specific output language regardless of user preference. This is a natural-language locale policy concern because the skill does not offer opt-in or choice for users who may want English or bilingual results.
- Content
Static analysis
No suspicious patterns detected.