Clear Prompt Engineering

Security checks across malware telemetry and agentic risk

Overview

This is a text-only prompt-improvement skill that may proactively help clarify vague requests but does not install code, access data, or take external actions.

Install this if you want the agent to proactively turn ambiguous requests into clearer prompts. Expect occasional clarification or rewrite suggestions on vague messages; review the suggested prompt before using it, especially when sensitive information is 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: 90% confidence
Finding: The skill declares that it activates automatically on 'vague input' without defining clear thresholds, scope boundaries, or user consent. In an agent setting, this can cause the skill to intercept a wide range of benign requests and rewrite user intent unexpectedly, creating prompt-manipulation risk, degraded reliability, and possible interference with higher-priority safety or task-routing logic.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal