Back to skill

Security audit

Engagement Inbox Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed social-inbox triage and draft-generation workflow that keeps posting and memory changes under human control.

Before installing, be aware that the skill is designed to handle potentially sensitive comments, DMs, mentions, and UGC permission evidence. Its instructions keep replies as drafts and require confirmation before saving results, so review exports and proposed memory writes before approving them.

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

Static analysis

No suspicious patterns detected.