Content Coach

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a creator-coaching aid, with only a routing-risk note about broad trigger language.

Install if you want a general creator or self-media coaching skill. Be aware it may activate for broad content, growth, or monetization questions, so use explicit wording when you want or do not want this skill involved.

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: 93% confidence
Finding: The trigger phrases are broad and generic, such as requests about content creation, growth, monetization, and account diagnosis, which can easily overlap with ordinary conversation and unrelated user intent. This can cause unintended skill invocation, leading the agent to apply this skill in the wrong context and produce irrelevant or steering responses that bypass more appropriate routing.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal