ClawHub
Back to skill

Security audit

Docker Encyclopedia

Security checks for vulnerabilities and agentic risk

Overview

This Docker helper is a disclosed documentation-and-notes workflow that writes a workspace-local cache and does not show hidden or malicious behavior.

Before installing, understand that this skill builds a persistent .Docker-Encyclopedia folder in each workspace and may save Docker docs plus environment-specific Docker notes. Do not let it record secrets, private registry credentials, tokens, or private URLs, and review proposed Docker operations before allowing changes to running containers, volumes, networks, registries, or daemon configuration.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill also includes workspace initialization/repair behavior via local directory creation, which is materially different from merely answering Docker questions. Hidden or under-disclosed scaffolding behavior can cause unintended filesystem modifications, especially in sensitive repositories or automation contexts where creating directories/files may affect tooling, commits, or trust boundaries.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill also includes workspace initialization/repair behavior via local directory creation, which is materially different from merely answering Docker questions. Hidden or under-disclosed scaffolding behavior can cause unintended filesystem modifications, especially in sensitive repositories or automation contexts where creating directories/files may affect tooling, commits, or trust boundaries.

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly instructs use of network access to fetch Docker documentation and file writes to cache content and create workspace structure, but it declares no tool scope or permission boundaries. That creates an unnecessary capability gap: an agent invoking this skill could perform network and filesystem actions without transparent, least-privilege constraints, increasing the chance of unintended writes, uncontrolled fetching, or misuse in a broader execution environment.

Static analysis

No suspicious patterns detected.