Back to skill

Security audit

阅读清单

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese reading-list helper with disclosed local storage and optional sharing/export features, with privacy caveats but no evidence of hidden or malicious behavior.

Install this if a Chinese-language reading-list workflow fits your use case. Before using share or export features, confirm exactly what will be sent to Notion, Obsidian, or other destinations, especially for private research topics, internal URLs, PDFs, notes, or tags.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The natural-language instructions, examples, and descriptions are entirely in Chinese, which effectively forces a specific language for interaction. The file does not offer multilingual use, user opt-in, or a justification that the skill is intended only for a Chinese-language context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises exporting reading-list data to external services such as Notion and Obsidian but does not warn users that article lists, notes, tags, and reading history may be transmitted outside the local workspace. This creates a privacy and data-governance risk because users may unknowingly sync sensitive research topics or internal references to third-party platforms.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.