Back to skill

Security audit

Director Beat Split

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language short-drama pacing and review guide with no code, install hooks, persistence, credential handling, or hidden execution behavior.

Install this if you want a Chinese-language assistant workflow for short-drama pacing and production review. Non-Chinese users may find it hard to use unless they translate or adapt the instructions.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is written to operate entirely in Chinese and instructs Chinese-language behavior by default, without offering any language preference or opt-in mechanism. This can undermine user autonomy, reduce accessibility for non-Chinese users, and create consent/usability issues if the agent applies the skill automatically in contexts where the user expected another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This markdown file presents all instructional content in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.