ai-github-radar

• Outcome: Pass
• Latest audit: May 28, 2026, 7:08 AM
• Version:
  1.0.0

Overview

This skill is a lightweight research prompt for summarizing public AI-tool and GitHub trend signals, with no code, credentials, persistence, or account-changing behavior.

Safe to install as a public research helper. Users should expect it to guide the agent toward AI-tool and GitHub trend analysis on broad AI-update requests, and should verify cited metrics before relying on them for business or investment decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger conditions are broad enough to activate on generic requests about AI updates, interesting innovations, or summaries, which can cause the skill to run outside its narrowly intended scope. This increases the chance of irrelevant tool invocation, overcollection of external data, and response steering toward this skill’s thesis even when the user did not specifically request GitHub radar-style analysis.

VirusTotal

51/51 vendors flagged this skill as clean.