Back to skill

Security audit

Neon

Security checks for vulnerabilities and agentic risk

Overview

The skill includes sensible Neon safeguards, but its automatic setup executes unverified remote code without clearly limiting the resulting changes.

Review setup before installing. Install a reviewed, verified CLI release yourself and retain the skill's confirmation requirements for Neon changes. Consider disabling automatic skill synchronization before first launch; the vendor documents OO_SKILLS_SYNC_DISABLED for this purpose. Remote installer behavior remains unverified, and OOMOL will mediate your connected Neon access. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)

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 installer execution rather than Neon data operations. Although installation can be a supporting implementation detail, nothing in this chunk establishes that the Oomol installer supports the declared Neon functionality. The downloaded script's subsequent behavior is not visible and cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into bash executes whatever script the endpoint currently serves, without an opportunity to verify it first. A compromised distribution endpoint could therefore gain code execution in the agent's host environment; the expected vendor domain and conditional setup make the purpose plausible but do not establish script integrity.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about the system-integrity implications.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs the agent to execute downloaded shell or PowerShell code without explicit installation approval, review, or integrity verification. Although this is legitimate dependency setup rather than evidence of malicious intent, compromised installer delivery could execute arbitrary code with the invoking user's privileges; restricting setup to a missing dependency reduces frequency, not impact.

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 93)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