ClawHub
Back to skill

Security audit

Layered Memory Architecture

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guidance skill for organizing agent memory, with no hidden code or automatic persistence behavior found.

Install this if you want help designing or auditing long-term agent memory. Before using it to migrate or edit an existing memory setup, tell the agent exactly which memory files or stores are in scope and review proposed persistent changes before applying them.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/scorecard.md (reported line 12)May include surrounding context.

md
- Are durable doctrine and raw notes separated?

High score:
- multiple clear memory layers with strong rules

Low score:
- one store plus loose tags/categories

Static analysis

No suspicious patterns detected.