Back to skill

Security audit

短剧本生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple short-drama writing skill with no code execution or data access; its only notable issue is a broad trigger phrase that may activate for general script requests.

Safe to install for short-drama or AI video prompt writing. Be aware it may activate on broad Chinese requests like “write a script,” so users may need to clarify when they want a different kind of script.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases such as '生成短剧', '写个剧本', and '帮我做个短剧', which can overlap with many ordinary creative-writing requests. In an agent routing system, this can cause the skill to activate unexpectedly, intercepting user intent and producing output outside the narrowest intended scope; while not directly leading to code execution or data exfiltration here, it increases the attack surface and can enable prompt-routing abuse or misfires.

Content

No source excerpt is available for this finding.