Security audit
AI KEY·该投哪条线
Security checks for vulnerabilities and agentic risk
Overview
The skill provides business-planning advice and saves disclosed notes, but requires configuration and a shared guide that are not included.
Review the missing configuration and shared interaction guide before use. Provide only relevant business records, enable pseudonym mode when appropriate, and check the configured memory location because analysis notes persist there. Keep business changes under your control. Both bundled files were inspected; the external configuration and shared guide remain outside this assessment.
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