ClawHub
Back to skill

Security audit

Dataify Bing Videos

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Bing video search helper that sends confirmed search parameters to Dataify using a user-provided API token.

Before installing, understand that confirmed searches will send your query and filters to Dataify and require a Dataify API token. Prefer passing the token for the current run unless you intentionally want to store it as an environment variable.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to read an environment variable for authentication and to make a live network request, yet no explicit permissions are declared. That mismatch can bypass least-privilege review and make operators unaware that invoking the skill may access secrets and external services.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger phrase 'Use when a user run a Bing video search' is broad enough that the skill may auto-invoke for many loosely related requests. Over-broad invocation increases the chance of unexpected tool execution, unnecessary parameter collection, and accidental transmission of user queries or tokens to an external API.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script transmits user prompt-derived search terms and filters to an external third-party service, but this file provides no user-facing disclosure, consent check, or data-minimization guard. In an agent setting, users may reasonably assume local processing, so silent exfiltration of prompt content to a remote API creates a privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.zh-CN.md:36