Nm Abstract Rules Eval

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown-only helper for reviewing Claude Code rule files, with no bundled code or evidence of hidden data access.

Install this if you want help auditing Claude Code rules. Be aware it may activate on generic requests about rules or validation, and review any separate Night Market or Claude Code plugin before installing because that external component was outside this artifact review.

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: 94% confidence
Finding: The trigger list includes generic terms like "evaluation," "rules," and "validation" without contextual constraints. In a manifest file, such broad activation phrases can cause unintended invocation because they overlap with ordinary discussion rather than uniquely identifying this skill's narrow purpose.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal