Security audit
LGD Crypto Guard（隐私计算守门）
Security checks for vulnerabilities and agentic risk
Overview
This skill needs review because its keyword checklist can approve systems lacking safeguards, while its instructions direct the agent to open services after approval.
Use this only as an advisory checklist with sanitized descriptions. Do not rely on PASS to establish privacy compliance or automatically deploy, expose, encrypt, or modify a service. Require independent evidence and explicit approval for those changes. The advertised model-checking API and enforcement integration are absent, and actual deployment behavior remains unspecified.
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