Back to skill

Security audit

Linux DO

Security checks for vulnerabilities and agentic risk

Overview

The reading features fit the stated purpose, but setup permits unverified remote code execution and under-disclosed changes to installed agent skills.

Review and approve CLI installation separately instead of allowing automatic setup. Select and verify a fixed release, review its changes to agent skills, and disable automatic skill synchronization if unwanted. OOMOL handles the hosted requests and account authentication. The remote installers and hosted backend were not verified; the evidence supports Review, not a finding of malicious intent.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code performs remote installation-script execution rather than Linux DO data access. Although dependency installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared purpose. The downloaded script's contents and resulting effects are not visible, so no specific downstream behavior or malicious intent can be established.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely retrieved script directly into bash executes whatever the endpoint returns with the agent process's permissions, without version pinning or independent integrity verification. Compromise of the distribution endpoint could therefore expose accessible credentials and files or enable persistent local changes; HTTPS alone does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

First-time setup instructs the agent to execute downloaded installer scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

When the CLI is missing, the skill directs installation through downloaded shell or PowerShell scripts without requiring informed user approval or checking their integrity. This expands a read-only task into local code execution and system changes; the missing-command condition limits when it occurs but does not make execution safe.

Content

No source excerpt is available for this finding.

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 82)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