Ci Cd Helper

Security checks across malware telemetry and agentic risk

Overview

This is a simple CI/CD advice skill with no executable code, credentials, persistence, or hidden behavior.

Safe to install from a security perspective. Treat any generated workflows or deployment scripts as drafts: review permissions, secret handling, production targets, rollback behavior, and test in staging before running them.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill is activated by very broad example phrases like designing a pipeline, writing a GitHub Actions workflow, or generating deployment scripts, which closely match ordinary CI/CD requests. Without clear activation boundaries, the agent may invoke this skill in contexts involving sensitive repositories, production deployment, or privileged automation, increasing the chance of unsafe or over-scoped assistance.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill offers to generate automatic deployment scripts without warning that such output can affect live systems, infrastructure, or data. In a CI/CD context, even small mistakes in deployment automation can cause service outages, data loss, or unintended exposure of secrets, so the lack of a safety warning materially increases operational risk.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal