ClawHub
Back to skill

Security audit

DigitalOcean

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent DigitalOcean connector skill, but users should be cautious about its one-time CLI installation instructions.

Install only if you intend to let an agent manage your DigitalOcean resources through OOMOL. Review any destructive droplet lifecycle action before approving it, and consider installing the oo CLI through a verified or inspected method instead of directly piping a remote installer into a shell.

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 the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a supply-chain and remote-code-execution risk: if the host, network path, or script is compromised, arbitrary code would run immediately on the agent's system. In this skill context, that is more dangerous because the tool is intended to manage cloud infrastructure, so a compromised environment could lead to credential theft, command execution, or manipulation of DigitalOcean resources.

Content

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says to use this skill for "ANY DigitalOcean request" and "Whenever a task involves DigitalOcean," which is an extremely broad activation condition. It does not provide narrower trigger boundaries or negative examples, so ordinary mentions of DigitalOcean could be interpreted as invoking this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.