ClawHub
Back to skill

Security audit

Instagram auto reply comments with DMs

Security checks across malware telemetry and agentic risk

Overview

This skill clearly does what it claims: automate Instagram comment-to-DM funnels through Upload-Post, with sensitive messaging permissions disclosed.

Install only if you intend to let Upload-Post automate DMs from a connected Instagram Business account. Before starting any funnel, confirm the exact post, trigger keywords, message text, monitoring interval, and whether it should persist; avoid replying to all commenters unless that is explicitly intended, keep the API key private, review logs, and stop or delete monitors when finished.

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
91% confidence
Finding
The README promotes continuous monitoring of Instagram comments and automated private messaging but does not warn users about privacy expectations, consent, rate limits, platform policy boundaries, or the risk of sending unsolicited messages. In an agentic context, this omission can lead operators to deploy automated outreach that users may perceive as spam or surveillance, increasing compliance, account enforcement, and reputational risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.