Security audit
MedXpert-CONT-001 · 官网与内容运营规范
Security checks for vulnerabilities and agentic risk
Overview
This is a MedXpert content and website style guide with no bundled executable code or automatic publishing behavior.
Use this as a MedXpert-specific reference. Review content before publication, preserve appropriate third-party attribution despite its no-attribution rule, and inspect the separately supplied synchronization script before running it. Independent inspection found no bundled executable behavior; the external script remains outside this assessment.
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
