Back to skill

Security audit

短视频带货脚本生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language content-generation skill for short-video ecommerce scripts, with no executable code or hidden system access.

Installers should treat this as a Chinese-market ecommerce copywriting assistant. Review generated claims, prices, discounts, refund promises, and regulated-product language before publishing, because the skill itself notes that platform rules, advertising-law compliance, and live pricing must be checked.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill description, examples, and expected interaction patterns are written only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This creates a natural-language locale constraint without user opt-in, which matches the policy-violation category for language or locale requirements.

Content

No source excerpt is available for this finding.