Back to skill

Security audit

WhoisFreaks

Security checks for vulnerabilities and agentic risk

Overview

The lookup functions are appropriate, but automatic setup executes unverified remote code and may change other agents’ installed skills without clear user control.

Review setup before installing. Use a verified CLI release, approve its local changes separately, and consider disabling startup skill synchronization before its first run. Connecting WhoisFreaks entrusts OOMOL with account access and lookup requests. The remote installer and executable remain unverified; the reviewed artifact does not establish malicious intent.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote installer execution and contains no WhoisFreaks search or data-reading behavior. Nothing provided establishes the Oomol installer as a supporting dependency for WhoisFreaks, so this is an undeclared capability rather than a demonstrated implementation detail. The downloaded script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied chunk only invokes a login command; it does not search or read WhoisFreaks data or establish that this login supports WhoisFreaks access. Authentication could be a legitimate supporting step if that connection were shown, but the supplied code instead presents an unexplained authentication operation as its sole behavior. No credential theft or data exfiltration is established by this command.

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 with the agent process's local privileges, without version pinning or artifact verification. HTTPS protects transport but does not protect against a compromised distribution endpoint or malicious installer update; the PowerShell example has the same weakness. The missing-CLI prerequisite limits exposure but does not remove the risk.

Content

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

Fallback setup executes downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

A missing CLI triggers instructions to install software without first obtaining explicit approval for local system changes. Although this fallback is relevant to the connector and only runs after a failure, a request to read WhoisFreaks data does not itself authorize installing software or executing a remote installer.

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