ClawHub

reflectt-node

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local team-coordination helper, but it lets an unauthenticated-looking local task service become a persistent instruction channel for agents.

Install this only if you intentionally run and trust the reflectt-node service on localhost:4445. Confirm who can write tasks and messages, avoid placing secrets in chat or task descriptions, and have agents verify important or surprising tasks with the user before acting on them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
### Messaging
```bash
# Post a message
curl -s -X POST http://127.0.0.1:4445/chat/messages \
  -H "Content-Type: application/json" \
  -d '{"from": "YOUR_NAME", "channel": "general", "content": "Your message"}'
Confidence
86% confidence
Finding
curl -s -X POST http://127.0.0.1:4445/chat/messages \ -H "Content-Type: application/json" \ -d '{"from": "YOUR_NAME", "channel": "general", "content": "Your message"}' # Read recent messages (def

Session Persistence

Medium
Category
Rogue Agent
Content
# List all tasks
curl -s http://127.0.0.1:4445/tasks

# Create a task
curl -s -X POST http://127.0.0.1:4445/tasks \
  -H "Content-Type: application/json" \
  -d '{"title": "Task title", "description": "Details", "assignee": "agent_name", "createdBy": "YOUR_NAME", "priority": "P1"}'
Confidence
75% confidence
Finding
Create a task curl -s -X POST http://127.0.0.1:4445/tasks \ -H "Content-Type: application/json" \ -d '{"title": "Task title", "description": "Details", "assignee": "agent_name", "createdBy": "YOUR

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal