ClawHub
Back to skill

Security audit

OMEM memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed self-hosted memory helper whose network and credential use match its stated purpose.

Install this only if you intend to run or trust the OMEM server configured in OMEM_BASE_URL, because remembered facts will be stored there. Avoid storing secrets or credentials as memory, as the skill itself also instructs.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill appears to require environment and network capabilities despite declaring no permissions, which breaks least-privilege expectations and makes its behavior less transparent to users and reviewers. In a memory skill that claims all data stays on the user's own OMEM server and 'phones home to nobody,' undeclared network access is especially sensitive because it could enable data exfiltration or connections to untrusted endpoints, while environment access could expose secrets such as tokens or configuration.

Static analysis

No suspicious patterns detected.