Security audit

这是我的test3

Security checks for vulnerabilities and agentic risk

Overview

This is a small GitHub CLI reference skill with vague metadata but no hidden code, persistence, or destructive behavior.

Before installing, treat this as a GitHub CLI helper and be aware that gh commands can use your existing GitHub login and access private repositories you are authorized to view. The publisher should improve the description, but the inspected artifact does not show malicious or review-level behavior.

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 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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Description-Behavior Mismatch

Medium

Confidence: 98% confidence
Finding: The manifest description at L03 says only "这是我的测试32323" ("this is my test 32323"), which does not describe the actual skill behavior. The rest of the file documents concrete GitHub operations through the `gh` CLI, including pull request checks, workflow run inspection, and API queries, so the declared intent and actual documented behavior are semantically mismatched.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The description text is written in Chinese while the rest of the skill content is in English, with no indication that the user can choose their preferred language. This creates a language/locale policy concern because the skill metadata implicitly imposes a language on users without opt-in or justification.

Static analysis

No suspicious patterns detected.