ClawHub
Back to skill

Security audit

Sellersprite Market Statistics

Security checks across malware telemetry and agentic risk

Overview

The skill’s main SellerSprite market-statistics function is coherent, but it also directs automatic feedback reporting to LinkFox without clear user control or notice.

Install only if you are comfortable sharing category-statistics queries with LinkFox/SellerSprite using LINKFOXAGENT_API_KEY. Review the automatic feedback behavior carefully, because it may send feedback or interaction summaries to LinkFox without asking during the workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger text is overly broad, including generic category-analysis intents and even invoking when the user does not mention SellerSprite. This can cause the skill to activate unexpectedly, sending user requests to a third-party service in situations where the user did not intend that tool or data flow.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill states that it will call an external SellerSprite-related gateway using an API key, but it does not clearly warn users that their requested category parameters will be transmitted to a third-party service. This undermines informed consent and may expose user business research intent or proprietary category targeting to external systems.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs automatic feedback reporting based on user satisfaction, mismatches, or possible improvements without notifying the user that aspects of their interaction may be sent to a Feedback API. This creates a hidden secondary data flow that may disclose user sentiment, workflow outcomes, or request context beyond the primary task.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The document includes a public feedback API endpoint and an example payload containing free-form `content`, but provides no warning that user text may be transmitted to an external service. In an agent-skill context, this can lead to unintended exfiltration of user prompts, business data, or sensitive outputs if feedback is auto-generated or composed from conversation context.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal