Back to skill

Security audit

Prd To Issues

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward workflow for turning a PRD into GitHub issues, with the main impact being expected creation of real issues after user review.

Before installing or using it, confirm the agent is in the correct GitHub repository and authenticated as the intended account. Review the proposed issue titles, dependencies, and bodies carefully before approving creation, because the skill will create real GitHub issues.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.