ClawHub

Skylv Docker Helper

Security checks across malware telemetry and agentic risk

Overview

This is a small Docker helper prompt file with no executable code, but users should confirm any Docker build, push, container, or network changes before running them.

Install this only if you want Docker assistance. Before running suggested commands, review Dockerfiles and build contexts for secrets, confirm the exact image tag and registry before any push, and avoid exposing Docker daemon or registry credentials in untrusted workspaces.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The metadata uses broad tags, keywords, and trigger phrasing around generic Docker/container terms, which can cause the skill to activate in situations the user did not explicitly intend. Because this skill advertises capabilities like container management, image building, registry push, and network configuration, unintended invocation could lead an agent to propose or initiate impactful operational actions in the wrong context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The usage examples include high-impact operations such as building and pushing images to a registry and configuring container networks, but provide no warning, approval gate, or safety constraints. In an agent context, this increases the chance of destructive or externally visible changes being carried out without the user understanding the consequences, including publishing sensitive images or disrupting running environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal