Systeme.io

Security checks across malware telemetry and agentic risk

Overview

This Systeme.io skill is mostly coherent, but it can cancel subscriptions and some other account data changes without consistently requiring explicit user confirmation.

Install only if you trust OOMOL and intend to let an agent operate your Systeme.io account. Before any write, delete, enrollment, webhook, tag, or subscription action, require the agent to show the exact target, payload, and expected effect, then give explicit final approval, especially before canceling a subscription.

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: 90% confidence
Finding: This action documents a destructive operation that cancels subscriptions but provides no warning, confirmation requirement, or guardrails to ensure the caller has explicit user authorization. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions against customer billing/subscription data, especially because the skill encourages direct execution once a schema is fetched.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal