Insta Content Engine

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed social-content tool, but it gives an agent live posting authority and credentialed account access without enough safeguards.

Install only if you are comfortable giving the agent access to real social accounts, API keys, and public posting authority. Review every caption, media file, destination account, and action before running publish commands; avoid passing Instagram passwords on the command line; and do not feed untrusted search text into the shell-based helpers until command construction is hardened.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The script invokes shell commands via execSync and interpolates user-controlled query data into command strings. Although double quotes in the X query are escaped, shell metacharacters such as command substitution remain dangerous inside double quotes, and the Instagram path passes the query without robust escaping, creating command-injection risk if an attacker can control input.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill includes commands that publish directly to live X/Twitter and Instagram accounts, but it provides no explicit warning, confirmation step, or safe/dry-run guidance. In an agent setting, this increases the risk of unintended public posting, reputational damage, spam, or misuse of authenticated accounts.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The script performs a live Instagram post immediately once invoked, without any confirmation gate, dry-run mode, or explicit warning before the irreversible network action. In an agent or automation context, this can cause unintended publication of content, reputational harm, and accidental posting to production social accounts from malformed prompts or operator mistakes.

VirusTotal

66/66 vendors flagged this skill as clean.