Back to skill

Security audit

NPC Dialogue Writer Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple NPC dialogue writing guidance skill with no code execution, credential handling, persistence, or hidden data access.

Before installing, understand that this skill mainly adds reusable writing structure for NPC dialogue tasks. Avoid pasting private or sensitive material into prompts, but no hidden execution or privileged access was identified.

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

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The 'When to use' section describes activation in very broad terms such as 'structured guidance in the Game Writing area,' which overlaps with many ordinary requests and does not clearly distinguish when this specific skill should or should not be invoked. The file does not provide exclusion conditions or negative examples to narrow scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example prompt begins with 'Help me,' which is common everyday speech and can collide with unrelated user requests. Although it includes the skill name later, the phrasing still models an overly broad trigger style without clarifying boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.