Ink

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  0.1.0

Overview

This appears to be a legitimate Ink cloud-management skill, but it can steer agents into broad, high-impact cloud changes without enough scoping or approval guidance.

Install only if you intend to let an agent operate Ink cloud resources. Before using it, verify the logged-in Ink account, workspace, project, repo, branch, and region, and require explicit user approval for deploy, redeploy, delete, DNS, database, repo-token, and secret-changing commands.

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: 95% confidence
• Finding: The skill description says to use this skill whenever the user mentions broad terms like deployments, services, or databases, which can cause the Ink skill to activate for unrelated cloud or database requests. Over-broad routing can misdirect an agent into performing actions against the wrong platform or account context, increasing the chance of unsafe or unintended infrastructure changes.

VirusTotal

64/64 vendors flagged this skill as clean.