ClawHub
Back to skill

Security audit

LiveScript Protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing script-writing skill with disclosed persuasion tactics and no code, persistence, credential access, or hidden execution behavior.

Install only if you want help drafting livestream sales scripts. Treat generated urgency, scarcity, audience counts, testimonials, and authority claims as placeholders unless you can verify them, and do not use the skill to target vulnerable audiences or make prohibited product claims.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill is explicitly designed to generate high-pressure livestream sales scripts using scarcity, social proof, urgency, and commitment-escalation tactics, but it provides no user-facing warning or safeguards about manipulative persuasion. In context, the danger is heightened because the metadata schema operationalizes these techniques for repeated automated use, making it easy to scale deceptive or coercive marketing behavior even though the file also bans some overtly false claims.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.