ClawHub
Back to skill

Security audit

Amazon Product Search Api Skill

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-built for Amazon product search via BrowserAct, but it tells the agent to ask the user for an API key directly and may send product research queries to an external service without enough user-facing control.

Install only if you are comfortable sending Amazon search terms and filters to BrowserAct. Do not paste the BrowserAct API key into chat; configure BROWSERACT_API_KEY through a local environment variable or approved secret-management mechanism. Use explicit confirmation before running searches that involve confidential product, pricing, or market research.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill declares required environment variables and uses an external API-backed script, but does not clearly declare permissions for sensitive capabilities like network access and environment secret usage. This weakens governance and user awareness, making it easier for an agent to invoke external data transfer without explicit permission review.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill is described as something the agent should 'proactively apply' for a very broad set of product-related requests, which can cause over-triggering. In context, that means user queries may be sent to a third-party API and browser automation workflow without sufficiently clear user intent or consent, increasing privacy and policy risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not clearly warn users that their search keywords, brand filters, and resulting product data will be transmitted to BrowserAct's external API service. In this context, the omission is significant because the whole skill centers on third-party data processing and could expose user research intent or proprietary market-monitoring queries without informed consent.

Ssd 3

High
Confidence
97% confidence
Finding
The script tells the user to 'Provide it to me or set it as an environment variable,' which creates a social-engineering path for users to paste a secret API key directly into the assistant. In an agent setting, this is dangerous because credentials disclosed in chat can be retained in logs, exposed to downstream tools, or mishandled by the model.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.