Docker Analyzer

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does Docker inspection, but one command can execute local code if given a crafted image name.

Review before installing. Use only with Docker contexts you are comfortable exposing to the agent, and avoid passing image names or arguments copied from untrusted text until the optimize argument-handling bug is fixed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The command triggers `help`, `run`, `info`, and `status` are extremely generic and likely to overlap with normal conversation or other skills. Broad triggers increase the risk of accidental invocation, which is more concerning here because the skill appears to expose command execution around Docker image analysis.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal