Back to skill

Security audit

gtrk 智能口播剪辑

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent video-editing workflow with disclosed cloud uploads, charges, and local tool installation.

Use media and transcripts you are comfortable sending to Gitruck's cloud, check pricing with --dry-run, and verify downloaded tools against trusted upstream checksums. Both scanners reported no issues; SkillSpector's incomplete status reflects unresolved documentation and runtime-file references. This review covers the supplied instructions, not the external CLI's implementation.

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