Volcengine Ai

Security checks across malware telemetry and agentic risk

Overview

This skill matches its stated Volcengine AI purpose, but it includes a real-looking API key and unsafe credential persistence guidance.

Review before installing. Do not use the embedded API-key-like value; create and store your own Volcengine key securely. Avoid placing long-lived secrets in shell startup files on shared or backed-up systems, and only send prompts, images, videos, and URLs that are acceptable to transmit to Volcengine.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Medium
Confidence
99% confidence
Finding
The documentation embeds what appears to be a real API key and instructs users to export it directly. Even if intended as an example, publishing concrete credentials can lead to unauthorized use, billing abuse, and credential reuse risk if the same key is valid elsewhere.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill sends prompts, images, and video URLs to a third-party service but does not clearly warn users that their content will leave the local environment. This creates privacy and compliance risk, especially if users submit sensitive media, internal URLs, or regulated data without realizing it will be transmitted externally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The setup instructions recommend persisting the API key in ~/.bashrc without warning about credential exposure to other local users, shell history, backups, or accidental commits of dotfiles. This weakens secret hygiene and increases the chance of long-lived credential leakage.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal