Config Drift Scanner

• Outcome: Review
• Latest audit: May 29, 2026 at 9:38 PM UTC
• Version:
  1.0.1

Overview

This skill has a legitimate config-auditing purpose, but its examples can expose sensitive configuration and secrets in terminal output, temporary files, or CI logs.

Install only if you are comfortable letting the agent inspect selected configuration sources. Before use, require redaction by default, avoid raw .env or tfvars diffs in chat or CI logs, use read-only scoped Kubernetes credentials, verify the current cluster and namespaces, and delete any temporary files containing configuration data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly instructs users to print raw configuration data from .env files, Terraform tfvars, and Kubernetes ConfigMaps directly to stdout and into temporary/report files. These sources commonly contain secrets, tokens, internal endpoints, and other sensitive values, so this behavior can leak credentials into terminals, CI logs, shell history, shared artifacts, or support tickets during routine use.

VirusTotal

64/64 vendors flagged this skill as clean.