ClawHub
Back to skill

Security audit

Coolify

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Coolify connector helper, with disclosed write/destructive actions and confirmation guidance, though users should be cautious about the one-time CLI install command and third-party OOMOL account connection.

Before installing, make sure you trust OOMOL as a broker for your Coolify account and review the oo CLI installer rather than blindly running piped install commands. For day-to-day use, require explicit confirmation before deployments, restarts, stops, cancellations, or any destructive Coolify action.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software via a remote script piped directly into the shell (curl ... | bash), which executes unverified code from the network with the user's privileges. If the install endpoint, transport, CDN, or upstream distribution is compromised, this can lead to arbitrary code execution and full host compromise.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY Coolify request" and "Whenever a task involves Coolify," which is extremely broad and lacks boundaries or exclusion conditions. This can overlap with many routine mentions of Coolify and does not specify when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.