ClawHub

sensorpro.app

Security checks across malware telemetry and agentic risk

Overview

This is a real Sensorpro management helper, but it exposes live email, deletion, import, and account-management API actions without clear confirmation or scoping guidance.

Review before installing in any account with real customers or mailing lists. Use a dedicated least-privilege API user, protect the .env credentials, and require explicit confirmation of recipients, payloads, lists, and IDs before any send, broadcast, delete, import, opt-out, or account-user change.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly lists destructive contact-management endpoints such as DeleteContacts and ForgetMe without any warning, confirmation guidance, or note about irreversibility. In an agent skill context, this increases the chance of accidental or overbroad deletion of contacts or privacy-erasure actions against live production data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents live email-sending capability via SendEmail but does not warn that it can send real outbound messages to actual recipients. In an autonomous or semi-autonomous agent setting, this can lead to accidental spam, reputational harm, or unauthorized communications if used without explicit user approval.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal