ClawHub
Back to skill

Security audit

Agent Memory OS

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill helps organize agent memory files, and its persistence behavior is disclosed, purpose-aligned, and privacy-scoped.

Install this if you want an agent to maintain structured long-term and project-specific memory. Review where those memory files will be stored, keep private data out of public/shareable outputs, and require evidence before promoting project-specific lessons into global rules.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: agent-memory-os
description: Stop agents from "forgetting, mixing projects, and rotting over time" by giving them a practical memory operating system: global memory, project memory, promotion rules, validation cases, and a maintenance loop.
---

# Agent Memory OS

**Build an agent that gets more organized over time instead of more chaotic.**

Turn an agent's memory from **"a pile of chat history"** into a **long-term working memory operating system**.

## What problem this solves

A lot of agents look impressive in short conversations, then collapse under real work:
- they forget what matters
- active project

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The "Typical triggers" list uses broad natural-language conditions such as "a pattern appears multiple times" and "a workflow succeeds once and looks reusable" without defining thresholds or exclusions. In a markdown guidance file, this ambiguity can lead to inconsistent or unintended invocation of the promotion path.

Content

No source excerpt is available for this finding.