Cold Outreach

Security checks across malware telemetry and agentic risk

Overview

This is a writing-only cold outreach skill; the main risk is using its drafts for noncompliant messaging, not hidden code or data access.

Install only if you want help drafting outreach copy. Before using the output, confirm recipient data was lawfully obtained, honor consent and opt-out requirements, follow CAN-SPAM, GDPR/UK GDPR, TCPA, CASL, and platform rules where applicable, avoid sensitive personal data, and review all claims for accuracy.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill operationalizes cold outreach across email, SMS, and LinkedIn using prospect research, sequencing, and personalization, but provides no safeguards around lawful basis, consent, data minimization, or anti-spam/privacy compliance. This can enable users to process personal data and contact individuals in ways that violate regulations or platform policies, especially for SMS and automated multi-channel campaigns.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal