Nm Sanctum File Analysis

Security checks across malware telemetry and agentic risk

Overview

This skill gives an agent read-only instructions to map a project’s file structure, with no evidence of hidden code, credential access, persistence, or exfiltration.

Install this only if you want an agent to inventory a codebase. Start it from the specific repository or subdirectory you want analyzed, not your home folder or a broad parent directory, because it can list local paths and file-size or line-count metadata.

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
The trigger list includes very generic terms like "files," "analysis," and "codebase," which are common in ordinary developer requests. This creates a real risk of unintended invocation, causing the skill to activate outside its intended scope and potentially steer workflows or run shell-oriented guidance when the user did not explicitly request this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal