Security audit
Deepvista Persona Knowledge Worker
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed DeepVista knowledge-work workflow; its main risk is that chat and automatic memory may retain sensitive work content.
Install only if you are comfortable using DeepVista for work notes and AI chat. Avoid sending secrets, credentials, regulated data, or confidential business information unless your organization approves, and review DeepVista memory controls before relying on automatic memory.
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.