Nm Pensive Code Refinement

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed code-refinement helper that scans project source code for quality issues and does not show hidden, destructive, or data-exfiltrating behavior.

Install this only if you want an agent to inspect source code in the active project and possibly produce reports with code snippets. Review optional Night Market/Claude Code plugin integrations separately before enabling them, and keep generated reports private when working with proprietary code.

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
95% confidence
Finding
This manifest-style markdown front matter defines triggers such as "refactoring," "algorithms," "craft," and "anti-slop" without clear scope constraints or exclusion conditions. Several of these are generic terms that could match common discussion about code or quality, increasing the chance of unintended invocation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal