ClawHub
Back to skill

Security audit

Reply.io CLI

Security checks across malware telemetry and agentic risk

Overview

This Reply.io skill appears purpose-aligned, but it gives an agent live campaign and contact-changing authority without enough built-in scoping or confirmation guidance.

Install only if you want the agent to access and potentially modify your Reply.io account. Use the narrowest API key available, avoid exposing it broadly in default agent environments, and require explicit confirmation before creating contacts, enrolling or removing contacts, or starting and pausing sequences.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This is a markdown file, so SQP-2 applies to missing user-facing warnings in the skill description. The document lists state-changing commands such as starting sequences, creating contacts, enrolling/removing contacts, and pausing campaigns, but it does not warn that these are live, potentially impactful actions affecting user data and campaign behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.