insta-post

• Outcome: Review
• Latest audit: May 28, 2026, 11:36 AM
• Version:
  1.0.1

Overview

This skill appears intended for Instagram posting, but it can publish to a logged-in account automatically, so it needs careful review before use.

Install only if you are comfortable letting an agent control a logged-in Instagram tab and publish real posts. Before each run, explicitly verify the target account, selected media paths, caption, and collaborators, and do not allow unattended posting.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The skill description understates important operational behavior: it relies on a live logged-in Instagram session via a local browser debugging endpoint and can publish content to a real account. That mismatch is dangerous because users or orchestrators may invoke the skill without understanding it can directly control an authenticated browser session and perform irreversible posting actions.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The invocation description is broad enough to match common requests about Instagram content creation or uploads, increasing the chance of accidental activation. In this context, accidental invocation is meaningful because the skill can drive a logged-in browser and publish to a live social-media account.

Missing User Warnings

High

• Confidence: 96% confidence
• Finding: The documentation does not clearly warn that the skill will act through an already authenticated Instagram session and may publish content immediately to a live account. This is dangerous because users may assume a draft or sandbox flow, while the skill's actual behavior can cause unintended public posting, reputational harm, or account misuse.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The script performs the final Instagram share action automatically once invoked, with no explicit confirmation gate immediately before publication. In the context of a live authenticated browser session, this can cause unintended public posting if the caption, selected media, or target state is wrong, making the action irreversible or difficult to fully undo.

VirusTotal

66/66 vendors flagged this skill as clean.