Security audit
LGD Gov Guard（政务 AI 治理守门）
Security checks for vulnerabilities and agentic risk
Overview
The skill recommends automatically releasing government AI tasks using a checker that can pass descriptions explicitly stating that safeguards are absent.
Use this only as a self-assessment checklist. Require human review of actual authorization and evidence before permitting data sharing, public replies or policy decisions; its PASS result does not establish compliance. The scanner's partial-coverage gaps were investigated and do not indicate a missing executable payload. No malicious data transfer or persistence was found.
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