github-research-assistant

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:15 PM UTC
• Version:
  1.0.2

Overview

The only supported concern is broad repo-inspection tool guidance, which fits a repository-analysis skill and is not evidence of hidden or harmful behavior.

Install this if you are comfortable letting the agent inspect the target repository using available tools or CLI commands. Keep use scoped to repositories you intend to analyze, and review any proposed shell command or file mutation before allowing it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: The instruction to '善用 MCP、tool、skill、CLI 获取仓库信息' authorizes broad tool usage without limiting actions to read-only inspection of the target repository. In an agent environment, that can lead to overbroad access, command execution, network calls, or interaction with unrelated resources, especially if the model interprets CLI/tool use expansively.

VirusTotal

65/65 vendors flagged this skill as clean.