Instagram Messenger

Security checks across malware telemetry and agentic risk

Overview

This Instagram Messenger skill is not deceptive, but it delegates broad account access for sending messages, changing profile settings, and making raw authenticated API requests without clear safeguards.

Install only if you trust Membrane and intend to grant delegated access to the selected Instagram account. Before use, require explicit approval for any send, delete, profile-setting, reaction, read-receipt, media-send, or proxy request, and revoke the Membrane/Instagram connection when it is no longer needed.

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 skill documents multiple state-changing and potentially destructive Instagram Messenger actions, including deleting ice breakers, sending messages, marking messages as seen, and reacting to content, but provides no guidance to obtain explicit user confirmation before executing them. In an agent setting, this increases the risk of unauthorized message sends, profile changes, or irreversible deletions caused by prompt ambiguity, user misunderstanding, or over-automation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal