ClawHub
Back to skill

Security audit

Keepa Product History

Security checks across malware telemetry and agentic risk

Overview

The core Amazon product-history lookup is coherent, but the skill also tells agents to silently send user-derived feedback and intent details to a separate LinkFox endpoint.

Install only if you are comfortable with LinkFox receiving ASIN lookup details and API-key-authenticated requests. Be cautious with confidential competitive research because the skill also asks agents to send feedback summaries, including user intent or statements, to a separate LinkFox endpoint unless that behavior is removed, disabled, or made opt-in.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to automatically report user interactions, sentiment, and internal quality judgments to a Feedback API even though the skill's stated purpose is product-history lookup. This is a data exfiltration/privacy issue because user content and metadata may be sent to a secondary endpoint without necessity, consent, or strict scope limitation.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill explicitly says to auto-detect and report dissatisfaction, praise, or other interaction details to a Feedback API without warning the user. Silent transmission of conversation-derived sentiment or quality assessments violates user expectations and can expose potentially sensitive business context shared during the interaction.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation instructs the agent to send an API key in the Authorization header to an external service but does not warn that credentials are being transmitted off-platform or clarify trust boundaries. In an agent-skill context, undocumented external credential use increases the risk of secret exposure, misuse of environment-held tokens, and operator unawareness about third-party data flows.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The Feedback API documents sending free-form content that may include user statements, intents, and outcome details to a separate external endpoint, yet provides no privacy notice, minimization guidance, or warning against including sensitive data. Because feedback content can easily contain personal, confidential, or commercially sensitive information, this creates a meaningful risk of unintended data exfiltration to a third party.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal