Popeye Learning

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:29 PM UTC
• Version:
  1.0.1

Overview

This is a simple Chinese study-helper skill made of Markdown prompts, with no code, privileged access, persistence, or external data transfer.

Safe to install for normal study use. Be aware that common Chinese phrases may invoke it when you intended a general request, and avoid pasting sensitive personal, school, or business notes unless you are comfortable processing them in the chat.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger phrase “帮我记” is broad and overlaps with ordinary conversational language, which can cause the skill to activate when the user did not intend to invoke it. This can lead to prompt-routing confusion, unwanted behavior, or accidental disclosure of user content to the skill workflow, even though the skill itself appears non-malicious.

Vague Triggers

Low

• Confidence: 85% confidence
• Finding: The skill describes example trigger words and features but does not define firm boundaries for when it should or should not activate. Ambiguous routing rules increase the risk of accidental invocation, especially in normal study-related conversations, which can degrade reliability and cause unintended processing of user inputs.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger phrase "帮我记" is short, generic, and likely to appear in ordinary user conversation, so the skill may activate unintentionally outside the user's explicit intent to invoke this memory assistant. Unintended invocation can cause prompt-routing errors, unexpected disclosure of user-provided content into the skill flow, and reduced reliability of higher-priority safety or task-selection logic.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrase `整理笔记` is broad and closely resembles normal conversational requests a user might make outside a narrowly scoped skill invocation. This can cause unintended activation, routing ordinary user content into the skill unexpectedly, which may override user intent, produce surprising behavior, or process sensitive pasted notes without clear confirmation.

Natural-Language Policy Violations

Medium

• Confidence: 78% confidence
• Finding: The skill content is entirely Chinese and implicitly constrains prompts and outputs to Chinese without offering a user-selectable language mode. While not a classic security flaw, this can create unsafe misunderstandings, reduce transparency for users or reviewers, and increase the chance that policy, consent, or data-handling expectations are not clearly understood across locales.

VirusTotal

66/66 vendors flagged this skill as clean.