Security audit

Github Trending Cn

Security checks for vulnerabilities and agentic risk

Overview

The skill is not destructive, but it presents static mock GitHub trending data as if it were current GitHub trend monitoring.

Review this skill carefully before installing. It appears locally contained and non-destructive, but its output should be treated as sample data unless the publisher updates it to fetch real GitHub Trending data or clearly labels it as a demo/mock skill.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The description suggests a monitor/fetcher for GitHub trending repos, programming language trends, and open source dynamics/updates. The code does not access GitHub or any external source at all; it uses a predefined in-memory list of repositories. While it loosely matches the idea of showing trending repositories, it is materially incomplete versus the declared purpose because it does not actually retrieve live trends, does not analyze language trends, and does not provide open source updates beyond a static mock list. This is a description-behavior mismatch.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description lists trigger words as "GitHub、trending、开源、热门项目", several of which are broad terms rather than narrow invocation phrases. In particular, "开源" and "热门项目" are generic concepts that could overlap with ordinary conversation, and the file does not provide constraints or negative examples to clarify when the skill should or should not activate.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring claims this is a GitHub Trending fetcher, but the implementation does not fetch anything and only serves static sample entries. This mismatch increases the likelihood that users or agents will over-trust the tool's freshness and authenticity, making it a deceptive behavior issue even if it does not directly execute unsafe code.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises live GitHub trending and open-source updates, but it returns hard-coded mock repository data instead of current information. This is dangerous because users and downstream agents may trust the output as real-time intelligence, leading to misinformation, bad decisions, or improper automation based on fabricated data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.