Back to skill

Security audit

Awareness Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only reflection skill that tells an agent how to create selective self-reflection notes, with no executable code or hidden data movement found.

Install only if you are comfortable with the agent creating reflective notes from conversation context. Confirm where your agent's memory or awareness system stores those notes, especially if conversations may include sensitive personal or business information.

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.