Security audit
Interview Crash Coach / 面试突击教练
Security checks for vulnerabilities and agentic risk
Overview
This interview-prep skill is a normal, disclosed workflow that saves research and optional practice feedback only with approvals.
Before installing, confirm you are comfortable granting JishuDB write access for the selected knowledge base and review each prompt that asks to save personal answers, feedback, scores, or resume excerpts. Declining personal retention should still allow generic preparation and conversation-only practice.
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.