Back to skill

Security audit

DigitalOcean

Security checks for vulnerabilities and agentic risk

Overview

The DigitalOcean workflow has sensible approval controls, but setup executes unverified remote code and its required CLI can silently install additional agent skills.

Review and approve the CLI installation separately, using a verified release where available. Trusting this integration also means trusting OOMOL with connected DigitalOcean access. Before running the current CLI, consider setting OO_SKILLS_SYNC_DISABLED=1 to prevent its documented startup skill synchronization. The remote installers and hosted connector implementation were unavailable for inspection.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The visible behavior is execution of an external installer, not DigitalOcean resource management. Nothing in the supplied chunk establishes this installer as a supporting dependency for DigitalOcean tasks. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a downloaded script directly into Bash executes mutable remote code with the invoking user's privileges, without prior inspection or independent integrity verification. A compromised distribution endpoint could therefore execute arbitrary commands and access local credentials or files; the missing-CLI prerequisite limits exposure but does not remove the risk, and the PowerShell alternative has the same weakness.

Content

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources