Agent Cli Orchestrator

• Outcome: Review
• Latest audit: May 29, 2026 at 9:25 PM UTC
• Version:
  2.0.1

Overview

This AI CLI orchestrator has a coherent purpose, but it under-discloses sensitive local data handling and persistent configuration changes.

Review before installing. Use this only in repositories where you are comfortable letting configured AI CLI providers receive prompts, diffs, summaries, and task context. Avoid production secrets in `.env`, inspect or back up `~/.ai-cli-config.json` before running the scanner, and require explicit approval before routing sensitive project context to another AI CLI.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The script silently writes a persistent file into the user's home directory without prompting, backup, or explicit consent. In an agent-skill context, unexpected persistent state changes are more sensitive because users may expect inspection-only behavior, and an existing config could be overwritten or used by later automation in ways the user did not intend.

VirusTotal

66/66 vendors flagged this skill as clean.