Security audit

vue-latest-changelog

Security checks for vulnerabilities and agentic risk

Overview

This skill does a narrow, disclosed task: it fetches Vue's changelog from GitHub and saves the latest section locally.

Before installing, expect the skill to run a Node.js script that contacts GitHub and writes a local changelog file. It does not request credentials or install dependencies, but users who prefer non-Chinese instructions or a no-network workflow should review it first.

A.I.G

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill instructs the user to run a local Node.js script that fetches data from GitHub, which implies network capability, but the skill manifest does not declare any corresponding tool scope or permissions. This creates a trust and transparency gap: users or platforms may execute a skill with undeclared external access, increasing the risk of unexpected outbound requests or future abuse if the referenced script is modified.
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 written as mandatory guidance in Chinese, including '请遵循此规范获取相关内容' and '需在Node.js环境下使用', with no indication that another language can be used. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill description says it should obtain and organize the latest Vue version update information when requested, which naturally justifies network retrieval and parsing. However, this implementation additionally writes the fetched changelog section into ../assets/latest_changelog.md, a side effect not indicated by the manifest description.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The script emits user-facing strings in Chinese such as '未找到匹配内容' and '获取内容时出错', and logs '内容已写入文件'. This imposes a specific language on all users with no opt-in or documented regional justification, which matches the locale-policy violation category.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.