Back to skill

Security audit

Learn Deep

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only learning skill that gives structured study guidance and does not request sensitive access or run code.

Installers should expect this skill to take over many Chinese concept-learning prompts and produce a multi-perspective deep explanation. Use it when that default behavior is desired; it does not add code execution or sensitive system access.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are extremely broad (e.g. 'X 是什么', '讲讲 X', '理解 X'), which can cause the skill to activate for many generic educational requests rather than a clearly scoped niche. In an agent system, over-broad routing increases the chance of misinvocation, bypasses more appropriate specialized skills, and can lead to irrelevant or lower-quality handling of user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and examples are entirely Chinese, which can imply a fixed language/locale behavior. There is no explicit opt-in, language selection mechanism, or justification that this skill is intentionally region- or language-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Declaring the skill as the 'default entry' for broad learning requests creates ambiguous boundaries and encourages it to supersede other skills whenever the user asks to understand a concept. That kind of default catch-all behavior is risky in orchestration because it can dominate routing decisions and make agent behavior less predictable or controllable.

Content

No source excerpt is available for this finding.