SMB Sales Boost — B2B Lead Database of SMBs for Cold Outreach & GTM

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SMB lead-generation API skill with disclosed API-key use, lead exports, recurring email delivery, and billing actions, but users should treat exports and billing settings carefully.

Install only if you trust SMB Sales Boost with your API key, lead data, and billing authority. Use previews and credit caps before exporting, keep exported files in secure locations, verify email schedule recipients, and require explicit confirmation for purchases, plan changes, and auto top-up settings.

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 (4)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest/skill description says purchases create real Stripe charges, but it omits several billing-management capabilities present in the API, including purchasing credits, enabling auto top-up, changing plans, and canceling subscriptions. This matters because an agent or user may not realize the skill can trigger ongoing or additional financial commitments beyond a one-time subscription purchase, reducing informed consent around monetary actions.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The API supports automated email schedules that distribute exported lead data to arbitrary recipients, but the skill metadata only mentions exports and does not clearly disclose persistent automated delivery/sharing behavior. Because exports contain PII such as phone numbers and email addresses, undisclosed automated forwarding materially increases the risk of unintended third-party disclosure and ongoing data exfiltration.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
Lead export and email delivery features handle sensitive business contact data, including phone numbers and email addresses, but the API descriptions do not include strong user warnings about privacy, downstream sharing, or recipient exposure. In an agent setting, this raises the chance that users will authorize bulk export or scheduled delivery without understanding that personally identifiable contact data is being packaged and sent onward.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The auto top-up feature explicitly enables automatic off-session charging of a saved payment method, yet there is no strong warning in the skill context that this can create future autonomous charges after initial setup. In an agentic environment, hidden autonomous billing behavior is especially dangerous because a user may approve a configuration change once without appreciating that subsequent charges can occur without further interaction.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal