Back to skill

Security audit

MoePeek AI Transcript

Security checks for vulnerabilities and agentic risk

Overview

MoePeek is a disclosed macOS translation app skill, with privacy considerations around clipboard, OCR, and third-party translation providers but no hidden or malicious behavior in the artifacts.

Before installing, users should understand that selected text, clipboard contents, and screenshot OCR may include sensitive information. Use local/on-device providers for confidential material, review the GitHub release before installing, and avoid sending private content through third-party translation services unless acceptable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The markdown file advertises translating selected text, OCR-captured screen content, and clipboard contents, all of which may involve user data or sensitive on-screen information. It does not provide any warning or disclosure that some translation backends listed later may transmit content to external services, which is the type of user-impact warning expected for markdown descriptions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises OCR, clipboard translation, and multiple third-party translation providers, all of which can involve processing sensitive user-selected text, screenshots, or clipboard contents. Because the description highlights privacy for Apple translation but does not warn that other configured providers may transmit data off-device, users could unknowingly expose confidential information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language content is written in Chinese throughout the README, which can amount to a language/locale constraint when no alternative language option or explanation is provided. The policy requires either user opt-in for a fixed language or a clearly documented justification for the locale limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing descriptive and instructional text in the skill file is presented only in Chinese, with no indication that language selection is optional or that the skill is intended exclusively for a Chinese-speaking audience. Under the language/locale policy, forcing a single language without user opt-in can be a policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.