Back to skill

Security audit

Recall Markdown Memory

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only helper for retrieving relevant Markdown memory sections and does not show hidden installation, persistence, data exfiltration, or destructive behavior.

Install only if you are comfortable letting Codex read relevant sections from Markdown memory files in the project. The skill is designed to be read-only and bounded, but memory files may contain private context, so use it with repositories where those files are appropriate for agent review.

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

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.