Security audit
gtrk 配音视频创作
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a clearly scoped video-creation workflow with disclosed cloud processing, charges, and user approval checkpoints.
Expect cloud processing of scripts and subtitles and possible usage charges. Select only intended media folders, request commercial-only assets for commercial projects, and choose step-by-step mode if you want approval before each edit. Review referenced companion skills separately.
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
SkillSpector findings are pending for this release.