Back to skill

Security audit

迪士尼/皮克斯风格的动画视频脚本创作技能

Security checks for vulnerabilities and agentic risk

Overview

This is a single Markdown skill for creating animation script documents, with no code execution, credential use, network behavior, or hidden persistence.

Before installing, expect a Chinese-first animation-script helper that may create a Markdown file in the workspace. Ask it to use your preferred language and confirm the save path before allowing any file write.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and description are written to drive Chinese-language output and do not indicate that the user can choose another language. This can cause the agent to ignore or override the user's preferred language, reducing usability and potentially causing misunderstandings in safety-sensitive or business contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow mandates a Chinese-only interaction pattern for requirement gathering without documenting it as optional or user-configurable. In practice, this can make the skill inaccessible to non-Chinese users and may lead to incorrect requirements being gathered if the user cannot respond accurately in Chinese.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill instructs the agent to save a generated Markdown file to a specific path without requiring user confirmation. Even though the action is low risk in this content-creation context, automatic file creation can surprise users, overwrite expected workspace structure, or trigger unintended side effects in integrated environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.