Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- 该 markdown 文件包含自然语言输出政策：'全文使用简体中文'。按规则，若技能强制特定语言/locale 且没有提供用户选择、opt-in 或明确的合理地域限定，就属于自然语言政策违规。
Security audit
travel city chinese
Security checks for vulnerabilities and agentic risk
Overview
This skill is a Chinese-language travel research helper that uses web search and page fetching in a way that matches its stated purpose.
Install this if you want travel briefings written in Simplified Chinese and are comfortable with the agent performing live web searches and fetching travel-related pages. Verify critical visa, entry, price, and schedule details against the official sources it cites before making bookings.
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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Static analysis
No suspicious patterns detected.