Back to skill

Security audit

Amplitude

Security checks for vulnerabilities and agentic risk

Overview

The Amplitude features fit the stated purpose, but setup directs the agent to execute an unverified remote installer without an explicit approval step.

Review and install the CLI separately before enabling this skill, using a verified release and checking which agent skills it installs or updates. Connecting Amplitude entrusts OOMOL with credential handling and access to your analytics. The bundled instructions show no malicious behavior, but they do not establish the safety or exact changes of the remote installer.

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 performs remote script execution for an Oomol CLI installer, not Amplitude data search or retrieval. Nothing in the chunk establishes that this installation supports the declared Amplitude functionality, and the installer’s downstream behavior is not visible.

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 content without a pinned version, integrity verification, or review. A compromised distribution endpoint could execute arbitrary code with the agent's local privileges; the PowerShell alternative has the same issue, although the missing-CLI condition limits when this path is reached.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup fallback directs the agent to install software when the CLI is missing without requiring approval or explaining local system changes. Although conditional setup is appropriate for this connector, permission to read Amplitude data does not necessarily authorize executing an installer with the agent's local privileges.

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 79)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