Docker Encyclopedia

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.0

Overview

This Docker helper is transparent about fetching official Docker docs and keeping a local workspace cache, with no evidence of hidden or unrelated behavior.

Install only if you want a Docker-specific assistant that may fetch official Docker documentation and write a .Docker-Encyclopedia folder in your workspace. Review or disable note-taking if your Docker environment details are sensitive, and do not allow credentials, tokens, private URLs, or other secrets to be written into the cache or inventory files.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill directs the agent to perform network access and filesystem writes via `scripts/cache_doc.py`, `scripts/init_workspace.py`, and by storing cached docs and notes under `.Docker-Encyclopedia/`, but no explicit permissions are declared. Undeclared write/network capabilities weaken user awareness and policy enforcement, and could lead to unexpected workspace modification or remote fetching during normal use.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 81% confidence
• Finding: The stated purpose is a Docker documentation-first assistance workflow, but the skill also instructs the agent to create local directory structures, cache remote content, and persist operational observations. That behavioral expansion is security-relevant because users may invoke what appears to be an informational skill without realizing it performs side effects on disk and over the network.

Missing User Warnings

Low

• Confidence: 76% confidence
• Finding: The skill repeatedly instructs the agent to save consulted docs and local operational learnings into the workspace, but does not clearly warn at the point of use that this persists data. Even though the skill includes a brief secrets warning, silent persistence can still surprise users and may capture environment-specific operational details they did not intend to retain.

VirusTotal

59/59 vendors flagged this skill as clean.