Security audit

Github Trending

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public GitHub trending pages and summarizes repositories, with no executable code or hidden privileged behavior found.

Before installing, be aware that results are intended to be in Chinese and the skill may cache public GitHub trending results if the agent chooses to use its optional cache strategy. Its web access is limited to public GitHub pages needed for trend analysis.

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

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: L003 明确写明“始终用中文输出结果”，这是对输出语言的硬性限制。根据规则，若未提供用户语言/地区选择或没有清晰、合理的场景限定，则属于自然语言层面的语言政策违规。

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: L127 要求“输出必须使用中文，包括标题、字段名、描述等所有内容”，属于无条件强制特定语言。规则要求语言限制需有用户选择或有明确、合理、已文档化的限定；此处未体现。

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The summary text is explicitly bilingual in Chinese and English, which suggests a fixed language presentation rather than a user-selectable locale. Under the policy criteria, language constraints should either offer user choice or be clearly justified as region-specific.

Static analysis

No suspicious patterns detected.