Back to skill

Security audit

repo-agent-brief

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward repository-briefing helper that discloses its command use, local repo reading, and generated output files.

Before installing, be aware that using the skill runs an npm-hosted CLI against the current repository and may write summaries containing code or configuration snippets. Review generated brief files before sharing them outside your workspace, especially for private repositories.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.