Back to skill

Security audit

sustoiclab-heros-journey

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing-coach skill for Hero's Journey story structure, with no code execution, data access, persistence, or hidden behavior found.

Install this if you want a Chinese Hero's Journey narrative coach. Be aware it may activate on broad writing-structure requests, so invoke it explicitly when you want this framework and ignore it for unrelated editing or factual-writing tasks.

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
90% confidence
Finding

The trigger list contains broad terms such as '写作结构', '文章骨架', and '叙事结构' that could match many ordinary writing-assistance requests beyond the narrow Hero's Journey use case. This can cause the skill to activate unexpectedly, leading to prompt hijacking of unrelated conversations or misrouting users into a specialized workflow they did not request.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The usage guidance says to paste text and have the AI guide the user stage by stage, but it does not define clear boundaries for when the skill should not be used. Without scope limits, the agent may apply this framework to generic articles, non-narrative content, or broad writing tasks, increasing the chance of inappropriate activation and degraded assistant behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.