ClawHub

get-some-leads

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about managing Instantly.ai campaigns, but it can bulk-upload leads and activate outbound email automation without a clear final approval step.

Review before installing. Use a narrowly scoped Instantly API key, confirm that leads may lawfully be uploaded, require a preview of recipients and email content, set conservative send limits, and only activate campaigns after explicit human approval.

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
94% confidence
Finding
The trigger description is broad enough to match common phrases like 'email outreach' or 'campaign activation', which can cause the skill to be invoked when the user did not explicitly request Instantly.ai campaign operations. In this skill's context, unintended invocation is more dangerous because the skill can create campaigns, upload leads, and activate outbound automation using a live API key, increasing the risk of unauthorized bulk actions or privacy-impacting mistakes.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill provides operational steps culminating in lead upload and campaign activation but does not require an explicit user warning or confirmation before sending outbound email or processing lead data. In this context, that omission is significant because the skill enables privacy-sensitive data handling and real-world email dispatch, which can trigger compliance, consent, and reputational issues if done unintentionally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal