Instagram Publisher

Security checks across malware telemetry and agentic risk

Overview

This skill performs the Instagram publishing and direct-message actions it advertises, with sensitive credentials and external actions disclosed.

Install only if you trust this skill and MyBrandMetrics with the connected Instagram account, API key, DMs, and media you provide. Keep credentials out of committed files, prefer runtime arguments or environment variables in shared workspaces, and verify the exact account, caption, media, conversation ID, and message text before allowing posts or DMs.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 79% confidence
Finding: The workflow section allows broad natural-language activation for publishing and messaging actions without tightly defining trigger boundaries or requiring hard confirmation gates before execution. In a skill that can post public Instagram content and send direct messages, ambiguous activation increases the chance of unintended or prompt-injected actions that could publish media or message recipients without sufficiently explicit user authorization.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal