Security audit
百度地图地址·汽车后市场门店网络分析
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed automotive store-network analysis helper that uses a specific external API and does not include hidden code, persistence, or unrelated authority.
Before installing, be comfortable using a DDT API key and sending automotive location-analysis queries to the publisher's external API. Do not paste secret keys into chat or logs, and treat returned store/location data as a limited published snapshot rather than a complete market record.
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