Grok X Growth Agent

• Outcome: Review
• Latest audit: May 29, 2026, 9:39 PM
• Version:
  1.0.0

Overview

This skill appears to automate promotional replies on X/Twitter using user credentials, but its controls and credential-safety guidance are not clearly scoped enough for that level of access.

Review this carefully before installing. Only use it with a test or low-risk account, confirm it cannot post without explicit approval, store credentials in a protected secret manager or ignored local environment file, and check X/Twitter automation and advertising rules before enabling affiliate replies.

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
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description frames the agent as operating continuously and autonomously on X/Twitter, but it does not define explicit trigger boundaries, approval gates, or scope limitations for when posting actions may occur. In a social-media automation context, vague activation semantics increase the risk of unintended posting, misuse of connected credentials, and policy-violating behavior at scale.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill promotes autonomous generation of affiliate-link replies on X but omits a clear warning that automated posting can trigger account penalties, API enforcement, spam classification, or suspension. The surrounding context makes this more dangerous because the stated purpose is monetized engagement automation, and the claimed 'ThumbGate' safety controls may create false confidence while still facilitating behavior that can violate platform rules.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The guide instructs users to place highly sensitive credentials such as X OAuth client secrets and an xAI API key into the environment without any warning about secure storage, least-privilege handling, or avoiding accidental disclosure through logs, screenshots, shell history, or committed .env files. In this skill’s context, the risk is heightened because the agent is designed to autonomously post affiliate content using social-platform and AI credentials, so leaked secrets could enable account takeover, abuse of paid API access, spam campaigns, and reputational damage.

VirusTotal

65/65 vendors flagged this skill as clean.