Enigma

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Enigma connector skill that uses OOMOL's oo CLI and includes safeguards for write and delete actions.

Install only if you are comfortable connecting Enigma through OOMOL and allowing the agent to run oo CLI connector actions. Review payloads before create or suggestion actions, and require explicit approval before any delete action or first-time CLI installation.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The instruction to use this skill for "ANY Enigma request" is overly broad and can cause an agent to route all Enigma-related tasks through a high-privilege connector without clear scope limits. In context, this skill supports read, create, update, and delete operations, so broad auto-invocation increases the chance of unnecessary access to sensitive data or unintended state-changing actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal