Security audit
jev-desktop
Security checks for vulnerabilities and agentic risk
Overview
The skill is a transparent desktop-automation guide that discloses its remote screen-data sharing and does not show hidden persistence or deceptive behavior.
Before installing, be comfortable with a tool that can operate desktop apps and transmit screen metadata and some field values to a remote API. Use it only with trusted companion scripts and agent-desktop binaries, avoid private documents or filled forms unless necessary, and prefer --no-values for sensitive workflows.
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
Static analysis
No suspicious patterns detected.