Wip Readme Format

Security checks across malware telemetry and agentic risk

Overview

This README formatter is mostly coherent, but it contains a real shell-command injection risk when deploying in a repository with crafted README-init filenames.

Install only if you are comfortable running a README-writing CLI on repositories you trust. Use --dry-run or --check first, review the generated README-init files, and avoid --deploy on untrusted repositories until the git status check is changed to a safe argument-array call.

SkillSpector

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

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The deploy review check builds a shell command with a filename interpolated into `execSync`, which means repository-controlled filenames are passed through a shell. Although the tool filters for names starting with `README-init-` and wraps them in quotes, shell metacharacters such as embedded quotes can still break out of the quoted context and cause command injection if a malicious repository contains crafted filenames.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal