ClawHub
Back to skill

Security audit

tulimoa-gateway

Security checks across malware telemetry and agentic risk

Overview

This skill clearly connects agents to a remote Tulimoa MCP gateway with persistent memory, and the sensitive behavior is disclosed and aligned with that purpose.

Install only if you want this agent to use Tulimoa's remote gateway and durable memory. Avoid storing secrets or regulated data, review which SaaS tools are connected in the Tulimoa dashboard, and use the provided forget/export/erase controls when memory should not persist.

SkillSpector

By NVIDIA
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
93% confidence
Finding
The skill explicitly promotes persistent memory across turns and sessions, but the top-level description does not clearly warn users that conversation-derived facts, IDs, goals, and plans may be retained beyond the current interaction. This creates a meaningful privacy and consent risk because users may disclose sensitive operational or personal information without realizing it will be durably stored and reused later.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill routes agent activity to a remote endpoint at gateway.tulimoa.com and describes federated SaaS access and memory features, but it does not prominently warn that user or system-derived data may be transmitted to an external service. Because the skill encourages recalling, remembering, checkpointing, and multi-tool orchestration, agents may send sensitive context, identifiers, or workflow data off-platform without clear disclosure to the user.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.