Back to skill

Security audit

IP2Proxy

Security checks for vulnerabilities and agentic risk

Overview

The IP lookup workflow fits its purpose, but its setup fallback instructs the agent to execute unverified installation scripts without a clear approval step.

Use an existing CLI installation or separately review and approve a verified installation before allowing lookups. Check whether setup installs other agent skills, and submit only IP addresses you may share with OOMOL and IP2Proxy. The external installer payloads and live connector implementation 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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote software installation, not IP2Proxy searching or data retrieval. No connection between this installer and the declared IP2Proxy functionality is established in the supplied chunk, so this is an undeclared capability rather than a demonstrated supporting implementation detail. The downloaded script's further behavior cannot be determined from the provided code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk performs only a login operation and shows no connection to IP2Proxy. Authentication could support a data-access skill, but the supplied code does not establish that relationship or implement the declared search/read behavior.

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 remote script directly into Bash without a pinned version, independent integrity verification, or review; the PowerShell alternative has the same execution pattern. If the distribution endpoint or release process is compromised, attacker-controlled code could access files and credentials or modify the host under the executing account.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

The lookup workflow lacks a privacy warning about transmitting IP addresses to third-party services.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to execute lookups through OOMOL and IP2Proxy but does not warn that the queried IP address is disclosed to those services. Labeling untagged reads as safe to run directly overlooks this privacy consequence, even though the lookup does not modify data.

Content

No source excerpt is available for this finding.

Automatic CLI setup executes downloaded scripts without warning about system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When the CLI is missing, the fallback instructs the agent to execute a downloaded installer without explicit approval for installation or its system changes. This expands a read-only lookup into local code execution with the agent's privileges; the conditional trigger reduces exposure but does not remove the risk.

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 76)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