Plan First

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only planning skill that is broad but does not install code, request secrets, persist, or perform hidden actions.

Install this as a low-risk planning aid, but review generated plans before allowing an agent to run steps that modify files, databases, accounts, or production systems. If broad auto-activation becomes noisy, keep the skill manually invoked or narrow its activation rules.

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: 88% confidence
Finding: The skill description is extremely broad, covering coding, writing, analysis, and general problem-solving tasks. In agent systems that auto-select skills from descriptions, this can cause the skill to activate for many ordinary prompts, unexpectedly inserting its workflow into unrelated tasks and expanding the attack surface for prompt-driven misuse or interference.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal