Security audit
Autonomous Timeline Video Editor
Security checks for vulnerabilities and agentic risk
Overview
The skill describes a clearly disclosed video-editing service with project-scoped edits and optional plan approval.
The supplied scanners reported no findings, and independent inspection found coherent editing instructions. Protect your API key, share only media you are comfortable having Levea process, and enable requirePlanApproval to review edits first. Review the separately installed plugin or MCP server because its code is outside this artifact.
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