Cold Email Outreach

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it can bulk upload contact data into an outbound email campaign with little user review or control.

Review the target CSV and campaign carefully before running. Use only contacts you are authorized to process and contact, keep API keys private, test with a small CSV first, and consider adding a dry-run/confirmation step before uploading leads to Instantly.

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 (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly automates collecting prospect data, verifying email addresses through Hunter, and uploading leads to Instantly, which means user-supplied contact data is transmitted to multiple external services. Because the skill documentation does not clearly warn users about these third-party disclosures, data handling, consent, or compliance obligations, it creates a real privacy and governance risk rather than a purely theoretical issue.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script sends each lead email address to Hunter's external verification API automatically, with no consent prompt, disclosure, or configuration gate indicating that lead data will be shared with a third party. This creates a privacy and compliance risk because operators may process exported contact data without realizing it is being transmitted off-platform to another vendor.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The script uploads personal and company data directly into an Instantly campaign and the output explicitly encourages launching outreach, but there is no safeguard, review step, or warning that contacts are being enrolled into a live outbound workflow. This is dangerous because a user can unintentionally add scraped/imported leads to an active campaign, creating privacy, compliance, and reputational harm through unsolicited messaging at scale.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal