Security audit
Drive Cli
Security checks for vulnerabilities and agentic risk
Overview
The skill provides clearly scoped access to chosen Google Drive folders, with explicit controls for edits and document sharing with a model.
Choose the intended profile and imported folders, and use read-only mode when you only need search and reading. Memory extraction sends document text to your configured model. Enable write access or MCP serving only when needed. Both scanners reported no findings, and independent inspection covered the complete supplied artifact; the separately installed package's runtime behavior remains unverified.
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