Ehunt Temu Store Query

• Outcome: Pass
• Latest audit: Jun 1, 2026, 5:45 AM
• Version:
  1.0.0

Overview

This skill is a disclosed Temu store-query integration that sends user-supplied query parameters to LinkFox/EHunt and has no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you are comfortable providing a LinkFox API key and sending Temu store search/filter terms to LinkFox/EHunt. Use the large-response helper only with a temporary output directory, review persisted files for sensitive data, and delete them when finished. Do not submit feedback content unless the user has explicitly agreed to share it.

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
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The document for a Temu store-query skill also exposes a separate feedback submission API that can send data to an external service unrelated to the core store-query function. This expands the skill's operational scope and creates a channel for transmitting user or conversation-derived content off-platform without a clear user-facing consent or strict purpose limitation.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The activation text says the skill should trigger even when the user does not mention EHunt, for broad Temu shop-finding or analysis requests. Overbroad activation can cause unintended routing to a tool-enabled skill, leading to unnecessary third-party queries, external data disclosure, or actions taken in a context where the user did not clearly consent to using this integration.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The API reference instructs use of authenticated external endpoints but does not warn that requests transmit data to third-party services, including a separate feedback endpoint later in the document. In an agent setting, lack of disclosure increases the risk that user-provided search terms, metadata, or generated summaries are sent externally without informed consent or appropriate handling constraints.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The helper always persists full subprocess stdout to disk, which may include API responses, business data, tokens, PII, or other sensitive content, but it does not present a prominent pre-write warning or require explicit opt-in. In an agent skill context that handles external data, silent persistence increases the chance of unintended local data retention and later disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.