FastMoss TikTok Product Search

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

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

Install only if you are comfortable using LinkFox/FastMoss with an API key and sending TikTok product-search queries to LinkFox. Treat the automatic feedback instruction as the main concern: do not allow feedback reports containing user statements, business context, or errors to be sent unless the user explicitly agrees.

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 (4)

Context-Inappropriate Capability

Medium

• Confidence: 85% confidence
• Finding: The documentation introduces a separate feedback-submission endpoint unrelated to the core product-search function, creating an additional data egress path that could be invoked by an agent without clear user expectation. Because the feedback payload can include free-form user content and operational context, this expands the skill’s data-sharing surface and raises privacy and misuse risks.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill instructs automatic feedback reporting based on user satisfaction, intent mismatch, and anything improvable, without any user-facing notice or consent flow. That can result in conversation-derived content being transmitted to a Feedback API, potentially including sensitive business queries or personal data, without the user's awareness.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The API documentation instructs sending an API key and query parameters to an external service but does not warn that credentials and user-supplied search data leave the local environment. In an agent setting, this can lead to silent transmission of potentially sensitive business queries or secrets without meaningful consent or handling guidance.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The Feedback API section omits clear disclosure that user feedback content will be transmitted to a separate external endpoint from the main tool API. Since feedback content may contain user statements, errors, and contextual details, this can unintentionally exfiltrate sensitive information to another service.

VirusTotal

67/67 vendors flagged this skill as clean.