ClawHub
Back to skill

Security audit

Vultr

Security checks for vulnerabilities and agentic risk

Overview

This Vultr skill is mostly purpose-aligned, but it can guide an agent to install a CLI through an unverified remote script before using a tool that can modify or delete cloud resources.

Review this skill before installing if you are comfortable trusting OOMOL with mediated Vultr operations. Prefer installing the oo CLI through a verified manual process instead of running pipe-to-shell commands, connect a least-privilege Vultr credential where possible, and require exact confirmation before any write or delete 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
96% confidence
Finding

The skill instructs use of a remote install command that pipes a fetched script directly into a shell (curl ... | bash). If the remote server, network path, or script contents are compromised, this results in immediate arbitrary code execution on the host running the skill, which is especially dangerous in an agent context with tool access.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says to use this skill for ANY Vultr request and instead of calling the API directly, which is an overly broad routing instruction. This can cause the agent to invoke a powerful skill for incidental Vultr mentions or low-trust contexts, increasing the chance of unintended read/write/destructive actions and reducing opportunities for narrower, safer handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.