Build ROSE tools using a container

• Outcome: Pass
• Latest audit: May 28, 2026, 12:34 PM
• Version:
  1.0.0

Overview

This skill appears to be a normal Docker-based ROSE compiler setup guide, with the main caution that its container can write to the current project directory when bind-mounted.

Install only if you are comfortable running Docker commands for a compiler toolchain. Treat the mounted project directory as writable from inside the container; use a disposable checkout, a narrower mount, or a read-only mount when you only need analysis and not build outputs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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: 91% confidence
• Finding: The skill instructs users to run a container with `-v $(pwd):/work`, which gives the container read/write access to the current host workspace. Because the skill does not warn that processes inside the container can modify or overwrite host files, users may treat the container as isolated when it is not. In this context, the risk is real because the container is explicitly used to build and run arbitrary analysis tools against user code, so containerized commands can affect host project contents.

VirusTotal

66/66 vendors flagged this skill as clean.