Back to skill

Security audit

MX

Security checks for vulnerabilities and agentic risk

Overview

The MX functions have clear approval safeguards, but missing software can trigger an unverified remote installer without a separate approval step.

Review and approve CLI installation separately before enabling automatic setup. Inspect a fixed installer release and check whether it adds other agent skills. OOMOL mediates your MX connection; use narrowly scoped access and retain the documented write and deletion approvals. The external installers and CLI runtime were not verified.

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
98% confidence
Finding

The supplied command installs software from an unrelated service and contains no visible MX operations or evidence that this installer supports MX functionality. Remote installer execution is not disclosed by the description. The downloaded script is not supplied, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable network response directly into Bash without checking a pinned version, trusted digest, or signature; the PowerShell alternative has the same issue. Compromise of the installer distribution path could execute arbitrary code with the agent's local permissions, exposing accessible files and credentials; HTTPS and an apparently relevant vendor domain do not establish artifact integrity.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Fallback setup executes a remote installer without warning the user about system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-command fallback directs the agent to install software without first explaining the system changes or obtaining installation approval. An ordinary MX request can therefore expand into local code execution and persistent environment changes, although the conditional fallback and declared Bash(oo *) restriction reduce exposure if that restriction is enforced.

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 80)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