Security audit

Emotion Router

Security checks across malware telemetry and agentic risk

Overview

This is a lightweight routing skill that changes how an agent responds to urgency, frustration, or confusion, without adding code execution, persistence, network access, or credential handling.

Before installing, consider that this skill may be invoked automatically when a message sounds urgent, frustrated, or workflow-confused. Its effects are limited to steering the agent's response style and route selection, so review its trigger behavior if you prefer fully explicit skill use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The manifest says this skill should route only on urgency, anger/frustration, or confusion related to the current work, but this file specifically defines an 'Urgency Route' triggered by speed/deadline/priority pressure. That behavior is materially different from an emotion-focused soft router and expands the routing basis from emotional state/workflow confusion to deadline pressure.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The default prompt says to use the skill for "clear urgency, strong anger/frustration, or active workflow confusion," which are broad emotional and situational cues rather than specific trigger phrases or constrained activation conditions. Without negative examples or narrower scope, this could overlap with many ordinary conversations and cause unintended invocation.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The manifest allows implicit invocation, but the file does not provide a precise, limited trigger list or contextual boundaries for activation. In combination with the broad natural-language description, this increases the risk of accidental invocation from common user speech.

Scope Creep

Low

Category: Excessive Agency
Content: copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
Confidence: 70% confidence
Finding: Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.