Ai Product Description From Image

Security checks across malware telemetry and agentic risk

Overview

This skill sends user-selected product images to x.ai to generate descriptions, which matches its stated purpose and is disclosed in the skill documentation.

Install only if you are comfortable uploading the product images you choose to x.ai for processing. Avoid confidential, regulated, or unreleased images unless that use is allowed, and protect the XAI_API_KEY because it authorizes API requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill declares use of an API key and outbound network access to api.x.ai, but the manifest does not explicitly declare permissions for those capabilities. This creates a transparency and policy-enforcement gap: users or platforms may not realize the skill can access secrets from the environment and send data off-host, including local image contents and derived metadata.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The script base64-encodes the full local image and sends it to x.ai for analysis, but it does not present a clear runtime warning or consent gate before transmitting potentially sensitive image contents to a third-party service. In this skill's context, external transmission is expected for functionality, but the lack of explicit disclosure increases the risk of unintended data exposure if users analyze private or regulated images.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal