Security audit
餐饮品牌竞对情报专家
Security checks for vulnerabilities and agentic risk
Overview
This is a scoped restaurant competitor-analysis skill that uses a disclosed external API with a user-provided key and shows no hidden code, persistence, or destructive behavior.
Before installing, confirm you are comfortable sending restaurant brand, address, and market-analysis queries to the disclosed gotoshop-ai.com API using your own DDT API key. The skill is designed to avoid full store-list extraction and to keep the key out of responses.
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