Send

Security checks across malware telemetry and agentic risk

Overview

This is a text-only pre-send communication review checklist with broad activation wording but no code, credentials, persistence, or authority to send messages.

Install this if you want a structured checklist for reviewing important messages before sending. Invoke it deliberately for pre-send review, and keep human approval for bulk, legal, HR, medical, confidential, or otherwise high-stakes communications.

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: 95% confidence
Finding: The manifest description uses very broad trigger terms such as 'anyone who communicates,' 'messages,' 'files,' and 'any communication before it leaves your hands,' which can cause this skill to activate for a large share of ordinary user requests. Over-broad routing increases the chance the skill is invoked outside its intended scope, potentially intercepting unrelated workflows and exposing sensitive communication content to logic that was not specifically requested.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal