ViralBrand Pro: X & LinkedIn Growth Engine

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:27 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed local content-planning skill that writes content logs, but it does not show hidden network access, credential use, or destructive behavior.

Install this only if you want an agent to maintain local content records and performance history in your workspace. Use explicit prompts, review proposed file changes before accepting them, and avoid storing sensitive business details in the content files unless you are comfortable with that local persistence.

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
• 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 (7)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The README instructs users to invoke the skill with a very natural phrase like 'Help me post 5 pieces of content for today.' In an agent environment, broad everyday phrasing can cause accidental activation during normal conversation, leading the skill to run generation workflows unexpectedly and potentially create or modify persistent content files.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The claim that the AI 'detects intent and runs the right protocol automatically' indicates ambiguous activation logic with no precise trigger contract. In a file-system-aware agent, implicit intent matching increases the chance of the wrong workflow executing, including data logging or state changes the user did not explicitly request.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The listed trigger phrases are generic conversational requests such as 'Analyze my recent performance' and 'Promote my consulting service,' with no scope, opt-in prefix, or exclusions. These phrases are common enough to be said in ordinary discussion, so the skill may activate unintentionally and perform generation, logging, or other automated behaviors.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README explicitly describes AI-created post logs and automatic appending to a feedback ledger, but it does not prominently warn users that the skill will create and modify persistent files. In a filesystem-enabled environment, silent persistence can surprise users, overwrite expectations about agent behavior, and retain sensitive business or audience data without informed consent.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger for content generation is activated by broad, everyday phrases like "help me grow," which can cause the skill to enter write/logging behavior when the user did not explicitly request that workflow. In this skill, activation is coupled to mandatory file reads and post-record creation, so accidental invocation can lead to unintended state changes and content generation.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The performance feedback trigger matches loose phrases like "here's the data" or "that post flopped," which are common conversational statements and may not indicate consent to modify persistent records. Because the mandated response includes matching records, updating metrics, changing status, and appending to a log, ambiguous activation can cause unauthorized or incorrect file updates.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly mandates persistent memory through the file system and states that it must read before writing and log every action, but it does not provide a clear user-facing warning or consent boundary around local data modification. This is dangerous because ordinary content-assistance interactions can silently create or alter files, producing unintended persistence, data integrity issues, and privacy concerns.

VirusTotal

62/62 vendors flagged this skill as clean.