Skill Creator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for creating, testing, improving, and packaging skills, with no evidence of hidden exfiltration, destructive behavior, or privilege escalation.

Install this only if you want an agent to help create or revise skills. Use a dedicated workspace, review any generated or modified SKILL.md before enabling it, avoid putting secrets into eval prompts or packaged folders, and verify any external local evaluation scripts before allowing the agent to run them.

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: 84% confidence
Finding: The skill explicitly recommends making descriptions 'pushy' and triggering on broad common-language contexts, which increases the chance of over-triggering on unrelated user requests. In context, this is more dangerous because the skill has powerful file and shell-oriented workflows, so accidental invocation can lead to unnecessary workspace creation, script execution, or process launching.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal