Back to skill

Security audit

Video Script Gen

Security checks for vulnerabilities and agentic risk

Overview

This is a simple video-script writing skill with marketing examples and payment links, and I found no code, credential access, persistence, or hidden automation.

Before installing, understand that this skill is only prompt guidance for creating video scripts. Use extra care for health, supplement, financial, legal, or other regulated promotions, and independently verify claims and required disclosures. The external PayPal, Telegram, and crypto payment references are commercial upsell links, not required runtime permissions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill’s invocation guidance is overly broad and can be triggered by ordinary content-writing requests without clear scoping or safety boundaries. This increases the chance an agent will apply the skill in unintended contexts, including persuasive or regulated-content generation, without the user understanding the associated risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly includes an example to create a TikTok script promoting a weight loss supplement, but provides no warnings or safeguards for health-related promotional content. This is dangerous because it can facilitate persuasive marketing in a regulated or harm-prone area without requiring substantiation, disclaimers, or review for misleading claims.

Content

No source excerpt is available for this finding.