Instagram Page

• Outcome: Review
• Latest audit: May 28, 2026 at 11:53 AM UTC
• Version:
  1.0.1

Overview

This Instagram management skill appears coherent and non-malicious, but it gives an agent comment-deletion authority without an explicit confirmation safeguard.

Install only if you are comfortable giving the agent access to your Instagram Business/Creator account via Meta credentials. Before using moderation features, require the agent to show the exact comment ID/text and get your explicit confirmation before any delete request; prefer hiding or reviewing comments first when possible.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The skill explicitly includes a destructive `DELETE` operation for Instagram comments but does not require a confirmation step or clearly warn that deletion is irreversible. In an agentic context, that increases the risk of accidental moderation actions from ambiguous user prompts or model misinterpretation, leading to unintended loss of user content and possible account-management harm.

VirusTotal

64/64 vendors flagged this skill as clean.