ClawHub
Back to skill

Security audit

Hybrid Memory

Security checks for vulnerabilities and agentic risk

Overview

This memory skill is coherent, but it encourages persistent logging of personal context without privacy guardrails or retention controls.

Review before installing if you do not want an agent storing personal context long term. Use it only with clear rules about what may be logged, avoid secrets and sensitive personal data, and confirm how Graphiti data can be reviewed and deleted.

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
94% confidence
Finding

The skill explicitly instructs the agent to log user facts and personal context into Graphiti group IDs such as user-personal without any warning, consent requirement, data minimization guidance, or retention constraints. In a memory skill whose purpose is persistent recall, this omission creates a real privacy and data-governance risk because sensitive personal or contextual information may be stored long-term and later retrieved or exposed more broadly than intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.