Back to skill

Security audit

直播带货话术生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese livestream sales-script skill with no code or privileged behavior; the main caution is to keep any urgency or scarcity claims truthful and compliant.

Install only if you want Chinese-language livestream commerce copy. Use it with truthful product, discount, and inventory information; do not rely on it to fabricate urgency, scarcity, endorsements, or compliance-sensitive claims.

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
94% confidence
Finding

The skill explicitly supports '促单话术' and '逼单技巧' using scarcity and pressure tactics, but provides no safeguards, disclosure, or policy limits against manipulative persuasion. In the context of a script generator for livestream commerce, this can directly facilitate deceptive or coercive sales behavior at scale, increasing consumer harm and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

All natural-language instructions and descriptions in the skill are Chinese, and the file does not state that the skill is region-specific or offer users a language option. Under SQP-3, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.