Back to skill

Security audit

Livestream Script Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese livestream sales-script skill with no executable behavior, but users should verify marketing claims before using its suggested copy.

Installers should understand this is a prompt-only writing aid for livestream selling. Before using generated scripts publicly, verify inventory, prices, promotions, giveaways, and product-performance claims against real evidence and applicable advertising or platform rules.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill explicitly generates livestream sales scripts, including urgency and conversion tactics such as limited-stock prompts, countdowns, giveaways, and efficacy-oriented product claims. Without clear warnings or guardrails against deceptive scarcity, unsubstantiated results, or non-compliant advertising language, users may be encouraged to produce scripts that violate platform, consumer protection, or advertising rules.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language description, usage, and examples all assume Chinese output and interaction, but the file does not state that the skill is region-specific or let the user opt into that language. This can violate language or locale policy when a skill implicitly forces a language without user choice.

Content

No source excerpt is available for this finding.