Reachmail

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate ReachMail integration, but it gives an agent broad authenticated control over email marketing and account-management data without explicit guardrails for high-impact changes.

Install only if you trust Membrane and intend to let an agent operate your ReachMail account. Use the least-privileged ReachMail account available, consider pinning the Membrane CLI version in controlled environments, and require explicit approval before sending campaigns, deleting records, bulk-changing subscribers or lists, or changing users and roles.

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 (1)

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: The skill explicitly documents a generic proxy request mechanism supporting mutating HTTP methods like POST, PUT, PATCH, and DELETE without requiring confirmation or warning about state-changing operations. In an agent context, this can increase the chance of unintended destructive or high-impact actions against a live ReachMail account, especially when the model falls back to raw API calls instead of constrained prebuilt actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal