ClawHub
Back to skill

Security audit

Building with MemorySync

Security checks across malware telemetry and agentic risk

Overview

This MemorySync integration guide is coherent and purpose-aligned, though users should notice it can direct an agent to contact MemorySync and mint limited evaluation credentials.

Install this only if you want agents to help build or evaluate MemorySync integrations. Before letting an agent mint an evaluation key or store/query memories, confirm the destination, the data being sent, and the quota or account effects; never allow secrets, tokens, passwords, or sensitive identifiers to be stored as memory.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly instructs the agent to mint evaluation API keys and consume a third-party service 'with no human in the loop'. That can create external resources, consume quotas, and potentially bind activity to the user's network or account context without explicit confirmation, which is risky even if intended for evaluation.

External Transmission

Medium
Category
Data Exfiltration
Content
MemorySync is the one platform where YOU (the coding agent) can provision a
working key with no human in the loop:

1. **Mint**: `POST https://api.memorysync.io/evaluation/keys` — body optional
   (`{"agent_caller": "claude-code"}`). A `201` returns `api_key`,
   `default_user_id`, `project_id`, `mcp_url`, `expires_at`, `limits`
   (add/retrieval/storage), and a `claim_command`. A `429` means the per-IP
Confidence
91% confidence
Finding
The skill directs outbound transmission to an external API endpoint to create evaluation credentials. This is a real security concern because it causes network interaction with a third party and may disclose metadata or create resources outside the local environment without an explicit approval boundary.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.