ClawHub
Back to skill

Security audit

Byted Data Search

Security checks across malware telemetry and agentic risk

Overview

This is a coherent business data lookup skill that uses Volcengine credentials and a remote API gateway, so users should understand where their queries and keys go.

Install only if you trust the publisher and the Volcengine gateway endpoint. Use least-privilege Volcengine keys, prefer environment variables over command-line secrets, do not override the gateway URL to an untrusted host, and avoid sending confidential business investigations through the skill.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger instructions are extremely broad, saying the skill should activate for essentially any request involving companies, industries, or supply chains, and even when coverage is uncertain it must probe data sources first. This can cause unintended invocation on ordinary business conversations, increasing unnecessary external queries, credential use, and potential disclosure of user intent to a third-party data provider.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The client sends both tool arguments and long-lived access credentials to a remote API gateway in custom HTTP headers, but the code provides no consent, disclosure, redaction, or policy checks before transmission. In this skill context, user queries may contain company-sensitive investigative requests, and sending raw AK/SK on every call expands exposure through logs, proxies, crash dumps, and any compromise of the gateway or surrounding infrastructure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.