Back to skill

Security audit

Metronome

Security checks for vulnerabilities and agentic risk

Overview

The skill reads Metronome data as advertised, but its fallback setup executes unverified software from the internet without a separate approval step.

Review the setup before installing. Prefer a reviewed, version-pinned CLI installation and require approval for local installation or agent-skill changes. Connecting Metronome gives OOMOL access to sensitive billing information. The external installers are not bundled and could not be retrieved, so their exact local effects remain uncertain.

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
99% confidence
Finding

The supplied command installs or bootstraps software from an unrelated service, and no Metronome functionality is shown. This is materially different from the declared data-search and reading purpose, not an established supporting implementation detail. The downloaded script's further behavior 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 HTTPS response directly into bash executes mutable remote content with the agent's local privileges, without a review or integrity-verification step. A compromised distribution endpoint or malicious installer update could therefore execute arbitrary commands and access local data; the PowerShell alternative has the same weakness.

Content

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

The fallback setup instructs the agent to execute downloaded installation scripts without warning the user about running remote code or changing the local system.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to install software and execute remote code without first obtaining approval for local system changes. Although conditional on the CLI being missing, this expands a read-only Metronome request into a potentially consequential installation operation without informed user consent.

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