Security audit

Creative Officer Tool Free

Security checks across malware telemetry and agentic risk

Overview

This appears to be a marketing and brainstorming helper, but it requests read and command execution permissions while saying those tools are not needed.

Review before installing. The skill content itself is not destructive, but it should not need command execution or file-read authority for creative brainstorming. Install only in an environment where those permissions are removed or tightly controlled.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Intent-Code Divergence

Medium

Confidence: 93% confidence
Finding: The skill documentation claims it is a pure Markdown skill that does not require exec or external tools, yet the manifest explicitly allows exec and read. This mismatch can mislead users or agent frameworks into granting broader capabilities than necessary, increasing the risk of unintended command execution or abuse if the skill is later modified or prompt-injected into using those tools.

Vague Triggers

Medium

Confidence: 79% confidence
Finding: The trigger condition is overly broad, covering common marketing, promotion, growth, and conversion discussions, which can cause the skill to activate in many ordinary conversations. Over-triggering is dangerous because it may inject this skill's instructions unexpectedly, potentially overriding user intent or increasing exposure to the skill's unnecessary tool permissions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.