Security audit
xinjianxue-skill-assistant-cn
Security checks for vulnerabilities and agentic risk
Overview
This skill is a clearly disclosed HTTP integration for a paid Chinese advisory/report service, with sensitive data and account credentials handled in ways that match its stated purpose.
Before installing, understand that this skill will use a one-time authorization code to bind the agent to your Xinjianxue account, then send personal profile details to the stated Xinjianxue API when you explicitly ask for a report. Only use it if you trust that service and are comfortable with the points-based charges and credential storage approach.
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
Static analysis
No suspicious patterns detected.