ClawHub

Cold Email Outreach

Security checks across malware telemetry and agentic risk

Overview

This skill is openly designed for cold-email outreach, but it combines contact scraping/enrichment and live outbound sending without enough safeguards or narrow user control.

Install only if you intentionally want a Resend-powered cold outreach tool and control the sending domain. Use dry-run first, review the exact recipient list and message copy, add unsubscribe and do-not-contact suppression controls, confirm you have a lawful basis to process contact data, and separately review any enrichment or follow-up scripts before using them.

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
88% confidence
Finding
The skill relies on an environment secret (`RESEND_API_KEY`) but does not declare permissions or clearly scope secret access. Undeclared secret usage reduces transparency and can cause the agent to access credentials unexpectedly, which is risky in a skill that automates outbound email sending.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The invocation text is broad enough to trigger on common requests about outreach, prospecting, or email automation, increasing the chance the skill is invoked in contexts the user did not clearly intend. In a high-impact workflow involving scraping, contact enrichment, and outbound cold email, overbroad triggering can lead to privacy-invasive or spam-related actions without sufficient user awareness.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly describes scraping websites, enriching contact information, and sending cold email campaigns, but it provides no user-facing warnings about consent, lawful basis, jurisdiction-specific privacy rules, or handling of personal data. In this context, the omission is dangerous because it normalizes potentially privacy-invasive collection and mass outreach workflows that can violate platform policy, anti-spam laws, or data protection obligations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal