Back to skill

Security audit

gtrk AI 情景动画分镜稿

Security checks for vulnerabilities and agentic risk

Overview

The skill creates animation storyboards and makes disclosed, project-scoped timeline changes with safeguards for existing edits.

Expect local project changes and review imported clips before continuing. Choose which material to submit to external generation services, and approve replacement only when you intend to discard manual edits. Some referenced general CLI documentation is not bundled.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The chunk performs timeline editing rather than generating AI-animation storyboard descriptions. Although the declared workflow mentions placing returned animation through gtrk ai-drama lay, these commands instead move and trim an arbitrary existing clip using gtrk patch. That is a materially different operation and is not demonstrated to be a supporting step in the declared generation or return-package workflow.

Content

No source excerpt is available for this finding.