Security audit
disease-investigation-zhcn
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent disease-research guide that uses a disclosed PatSnap MCP connection and does not show hidden, destructive, or unrelated behavior.
Before installing, confirm you trust PatSnap with the queries sent through its MCP service and protect the API key used in the configuration command. Expect the skill to make a lightweight connectivity check to PatSnap before answering disease-research questions.
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.