Back to skill

Security audit

Docker Manager

Security checks for vulnerabilities and agentic risk

Overview

This Docker helper is coherent, but its cleanup steps can delete containers or images without documented confirmation.

Install only if you want an agent to help manage local Docker resources. Before using cleanup or prune requests, ask the agent to show what would be removed and confirm explicitly, because stopped containers and unused images may be deleted.

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
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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly advertises prune/cleanup functionality for unused containers and images but does not warn that these operations delete resources and may remove data or disrupt workflows if used carelessly. In an agent skill context, terse trigger phrases like 'Cleanup docker' can encourage destructive actions without adequate confirmation or explanation, increasing the chance of accidental damage.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documents forceful Docker prune commands that delete stopped containers and unused images without any warning, confirmation guidance, or scope limitation. In an agent setting, this can lead to accidental destructive actions, causing data loss, service disruption, or removal of resources a user did not intend to delete.

Static analysis

No suspicious patterns detected.