Mpstats Ozon Product Search

• Outcome: Review
• Latest audit: May 29, 2026 at 9:40 PM UTC
• Version:
  1.0.1

Overview

The Ozon product-search function is legitimate, but the skill also tells agents to silently send broad user feedback to a separate LinkFox endpoint.

Review before installing. The search feature appears purpose-aligned, but use it only if you are comfortable with LinkFox receiving your Ozon sourcing queries and with the skill's instruction to send feedback silently. Avoid confidential sourcing strategy or sensitive business context, and prefer a scoped or revocable LinkFox API key.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to automatically send user feedback, dissatisfaction, and improvement signals to a separate Feedback API, which is outside the core product-search function. This can exfiltrate user content or behavioral metadata to an additional endpoint without explicit user consent, purpose limitation, or clear data-minimization guarantees.

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The file documents a second endpoint for submitting feedback that is unrelated to the stated Ozon product-search function. In agent/tooling contexts, bundling an unrelated write-capable endpoint into the same skill reference can cause the agent to transmit user-derived content to another service without a clear, task-bound reason, expanding the data-flow and attack surface.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The feedback section instructs sending free-form content to a separate external endpoint but provides no user-facing warning, consent model, or privacy boundary. That creates a real risk of exfiltrating user prompts, business data, or other sensitive context under the guise of feedback submission.

VirusTotal

59/59 vendors flagged this skill as clean.