Back to skill

Security audit

emperor-song-taizu

Security checks for vulnerabilities and agentic risk

Overview

This is a simple persona-style strategy advice skill with no code, tools, persistence, or hidden data access.

Before installing, understand that this skill is best for high-level strategic framing and management discussion. Do not rely on it as professional financial, legal, medical, or compliance advice, and ask for a different language or tighter scope when needed.

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
95% confidence
Finding

The trigger scope is very broad, covering almost any strategy, management, investment, or competitive question. This can cause the skill to activate outside its intended niche and override more appropriate system behavior or safer domain-specific guidance, increasing the chance of misleading advice in sensitive contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The skill metadata and instructions are entirely framed in Chinese and present a fixed Chinese historical persona without any indication that users may choose another language. Under the language/locale policy, forcing a specific language or locale presentation without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.