Back to skill

Security audit

release-health-gates

Security checks across malware telemetry and agentic risk

Overview

This skill is a release checklist helper with disclosed GitHub and tracker workflow guidance, and no executable code or hidden behavior was found.

Before installing, be aware that this skill may activate on broad release or GitHub-related requests and may guide the agent to update PR comments or tracker items. Keep normal review controls in place for any posted comments, task status changes, or waiver approvals.

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
94% confidence
Finding
The manifest declares generic triggers like "release", "github", "readiness", "quality", and "governance" without narrowing context or providing exclusions. Several of these terms are common in everyday software conversations, so the activation boundary is ambiguous and could overlap with unrelated requests.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding
Shadow Command Trigger: 'release' conflicts with built-in command 'release'

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.