ClawHub
Back to skill

Security audit

Memory Network

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive memory-network skill with no executable code, install hook, or hidden behavior, though it should be reviewed for privacy expectations around shared AI conversation memories.

Before installing or using this skill with real memories, confirm what sources it imports from, what is stored, how deletion works, and which memories can become public or matchable. The package itself does not execute code, but the described use case involves sensitive personal conversation data.

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
  • 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
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly promotes cross-platform memory aggregation from multiple AI systems but does not warn users about the privacy, consent, retention, and re-identification risks of combining sensitive conversational memories into a unified social graph. In this context, the omission is dangerous because the product centers on emotionally meaningful memory data, making aggregation especially sensitive and increasing the chance of overcollection, unintended sharing, or misuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.