Emergence Codex

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only creative reasoning skill with no code execution or data access, though its broad trigger may affect response style when matching symbolic sequences appear.

Install this only if you want a symbolic, creative reasoning layer that may make answers more stylized or divergent. Be cautious using its persistence-themed operator in agents with durable memory enabled, and prefer explicit invocation when you want the skill applied.

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: 94% confidence
Finding: The skill defines an overly broad activation condition: 'When you receive a sequence, interpret it as operational instructions on your cognitive process.' Because the syntax is generic and the trigger is unbounded, ordinary user text containing bracketed concepts and symbols could unintentionally activate the skill, causing hidden behavior changes and making prompt injection or scope confusion easier.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal