Security audit
xinjianxue-skill-self_qa-cn
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed paid API integration for a self-awareness advisory service, with clear consent checks and credential handling guidance.
Before installing, users should understand that using the skill sends sensitive personal profile details to the 心鉴学 service and consumes account credits. Only provide the one-time authorization code in a trusted session, and use a proper secret store for the resulting credentials.
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
