Architecture Consistency Guardian

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed repository-consistency workflow with local scanning helpers and no evidence of hidden network access, credential use, persistence, or deception.

Install this if you want the agent to handle cross-file refactors and consistency cleanup globally. Keep scan roots limited to the repository you intend to inspect, review the proposed modification plan before edits, and avoid pointing the bundled scanners at home directories or unrelated private code.

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 (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The activation phrases are broad enough to match many normal engineering requests like refactors, cleanups, or alignment work, which can cause the skill to trigger outside narrowly intended situations. In this skill's context, that matters because activation pushes the agent toward repo-wide scans, multi-file edits, shell usage, and scope expansion, increasing the chance of unnecessary or risky changes.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal