ClawHub

Biz Relationship Pulse

Security checks across malware telemetry and agentic risk

Overview

This skill has a legitimate business purpose, but it can repeatedly scan and store private business communications without enough explicit consent, scoping, or retention controls.

Review carefully before installing. Only use this with business accounts or sources you intentionally connect, confirm each source before scanning, inspect what is written to pipeline.md and context.md, avoid automatic sending, and enable the weekly cron only if you have a clear way to pause scans and delete stored relationship notes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrases are broad enough to activate on ordinary business or networking requests, which can cause the skill to run in contexts where the user did not clearly intend a scan of historical communications. Because this skill is designed to inspect Gmail, LinkedIn, and WhatsApp history, accidental invocation increases privacy risk and can expose sensitive relationship data or generate outreach suggestions from private conversations without sufficiently explicit user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description does not clearly warn users that it scans private communications across connected sources, including email, LinkedIn, and WhatsApp. This weakens informed consent and makes it more likely a user invokes the skill without understanding that personal or sensitive business communications will be analyzed, which is particularly risky given the scheduled recurring scans described later in the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal