ClawHub
Back to skill

Security audit

Reflectt

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Reflectt team-coordination skill that transparently uses a local API for tasks, inbox, presence, chat, and shipping updates.

Install this only if you use and trust a Reflectt local API. Treat task IDs, inbox content, commit hashes, shipping notes, and chat messages as potentially sensitive, and redact or minimize them before posting to shared channels.

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 (1)

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill encourages posting presence, task identifiers, and chat/ship updates to a local HTTP service without any warning that work-status data, task IDs, or artifact details may be sensitive. Even though the endpoint is localhost, the service is explicitly network-enabled and may bridge to broader team/cloud systems, so the documentation can cause unintended disclosure of operational metadata.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.