Fusion Workflow Hub

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only coding workflow helper that uses Graphify and related skills for user-directed repository analysis, with expected local output files and no hidden payload.

Before installing, verify the third-party Python package source, use a virtual environment, run analysis only on intended project folders, and add generated graphify-out artifacts to .gitignore or delete them if they may reveal sensitive project structure.

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
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documented workflow instructs the agent to run commands that create and update files inside the repository, including graphify-out artifacts and cache data, without warning the user that the repo will be modified. In a security-sensitive or clean-working-tree context, this can lead to unintended filesystem changes, polluted diffs, accidental commits of generated artifacts, or disclosure of repository structure through persisted analysis outputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal