Back to skill

Security audit

Learning Plan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language learning-plan generator with templates and a local Python example script, and I found no hidden, destructive, persistent, credential-seeking, or network behavior.

Install this if you want a Chinese-language study-plan generator. Be aware that its broad Chinese trigger phrases may activate for general study questions, and its current templates are Chinese-only unless the agent adapts them for another language.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are generic everyday terms such as '学习计划' and '怎么学习', which can match ordinary conversation and cause the skill to activate unintentionally. This can lead to prompt hijacking of unrelated user requests, incorrect routing, or unexpected behavior in multi-skill environments even though the skill itself is otherwise benign.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

All user-facing instructions and examples in the skill are presented in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language audience. This can conflict with language/locale policy expectations when a skill forces one language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. At L001 the file begins with a Chinese-only title, and the rest of the template content is also Chinese-only, with no indication that users may choose another language or that the limitation is intentionally region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This Python file contains user-facing natural-language content such as the module description and generated plan template in a single forced language. Under the policy, language-specific behavior should offer user opt-in or clearly justify the locale restriction, which is not present here.

Content

No source excerpt is available for this finding.