Senior Devops

Security checks across malware telemetry and agentic risk

Overview

The skill is a broad DevOps guide with placeholder scripts and no hidden execution, but users should review any production commands before running them.

Treat this as a DevOps reference/template rather than a working automation package. Before using any suggested Terraform, AWS, Docker, or Kubernetes commands, test in staging, review diffs and plans, and ensure cloud/IAM permissions are narrowly scoped.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 83% confidence
Finding: The skill advertises automated scripts that scaffold pipelines and infrastructure, which inherently implies writing files, but it does not declare any permissions or constraints around that capability. In an agent setting, undocumented file-write behavior increases the risk of unreviewed modifications to repositories, CI/CD configs, or infrastructure definitions that could introduce insecure changes or overwrite sensitive files.

Vague Triggers

Medium

Confidence: 78% confidence
Finding: The description is very broad and encourages use for many common DevOps tasks without defining safety boundaries, approval requirements, or environmental limits. In a high-privilege DevOps context, vague activation criteria can cause the skill to be invoked in production-sensitive situations where it may generate or recommend deployment and infrastructure changes without sufficient review.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal