Back to skill

Security audit

Popeye Learning

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese study-helper prompt skill that does not install code or access data beyond what the user provides.

Install this if you want a Chinese-language study assistant for notes, memorization, and review plans. Use explicit prompts if you want to avoid accidental activation, and avoid pasting sensitive private notes unless you are comfortable sharing them with the agent handling the request.

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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are common conversational terms such as '整理笔记', '帮我记', and '复习计划', which can plausibly appear in ordinary user requests and unintentionally activate the skill. This creates a prompt-routing and unintended invocation risk rather than direct code execution, but it can still cause the wrong skill to process user data or override expected behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill metadata and instructions are entirely Chinese-centric and do not indicate any fallback or language negotiation, which can force interactions into a language the user did not choose. This is primarily a safety/usability issue: language mismatch can cause misunderstanding of outputs, user intent, or disclosures, especially if the platform serves multilingual users.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrase 帮我记 is very broad and resembles ordinary conversational text, so it can cause accidental invocation of the skill in unrelated contexts. This increases prompt-routing ambiguity and may lead the agent to apply this skill when the user did not intend memory-assistance behavior, reducing reliability and potentially interfering with safer or more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The entire skill, including the title, trigger phrases, prompt template, and example dialogue, is written exclusively in Chinese and does not indicate that users may choose another language. Under the policy, language-specific behavior is a violation unless the skill provides opt-in or clearly documents a justified region- or locale-specific restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language policy checks apply to all file types. The file presents the title, trigger phrases, prompt template, and example dialogue only in Chinese, which can amount to a language constraint without user opt-in or an explicit statement that the skill is intended only for Chinese-speaking users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The skill content, trigger phrases, and prompt template are all presented in Chinese, and the file does not indicate that language selection is optional or that the skill is intentionally limited to a Chinese-language context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The activation phrases 整理笔记 and especially 帮我整理笔记 are natural-language requests that could plausibly appear in ordinary conversation. The file does not specify when the skill should not activate or provide narrower contextual constraints, which increases the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.