ClawHub
Back to skill

Security audit

short-drama-pro

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow writing-assistant skill for Chinese short-drama scripts and does not request tools, credentials, persistence, or system access.

Install this if you want help writing Chinese-style short dramas. Specify language, market, genre, format, and audience when you need a different style, because the skill naturally defaults to commercial Chinese short-drama patterns.

A.I.G

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

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description and theme guide are explicitly centered on Chinese short-drama creation and common Chinese-market genres, but they do not state whether this locale/language specialization is conditional on user preference. In ambiguous cases, this can bias outputs toward Chinese-language or culturally specific formats the user did not request, reducing user control and causing mismatched or exclusionary responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation condition is very broad: '当用户想要创作、改写、扩写或优化短剧内容时使用本 skill' can capture a wide range of general writing/editing requests without a strong discriminator. This can cause the skill to trigger outside its intended scope, steering unrelated writing tasks into this workflow and increasing the chance of inappropriate or over-applied behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.