Security audit
Vertical Short-Form Video Editor
Security checks for vulnerabilities and agentic risk
Overview
The skill provides clearly disclosed, user-directed video editing through an external service, with no hidden or unrelated behavior in the supplied artifact.
Use media you are comfortable making accessible by URL and processing through Levea. Review the separate plugin or MCP server before installation, protect its API key, and enable requirePlanApproval if you want to approve edits first. This review covers the supplied instructions, not the external software or service.
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