Viral Content Score

• Outcome: Pass
• Latest audit: Jun 2, 2026, 2:39 PM
• Version:
  1.0.0

Overview

This skill is a simple paid remote API for scoring social-media copy, with clear enough purpose but privacy, billing, and HTTP transport cautions.

Before installing or using it, assume any title or marketing copy you submit is sent to a third-party server over unencrypted HTTP and may incur a ¥0.50 charge per request. Do not send confidential drafts, client data, credentials, or regulated information, and use it only when you are comfortable with the provider and billing model.

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 (3)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs users to send arbitrary title/content data to a remote HTTP endpoint identified by raw IP address, but it does not warn that user input will leave the local environment and be transmitted to a third-party server. Because the feature also appears tied to paid invocation, users may unknowingly disclose sensitive marketing drafts or internal copy while triggering billable requests without informed consent.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The document states that each request is automatically charged, but it does not present a strong warning or consent checkpoint before use. This creates a risk of unauthorized or surprise charges, especially when an agent or user may invoke the skill assuming it is informational rather than billable.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The manifest defines a broadly callable remote skill but does not specify activation conditions, user-intent boundaries, or trigger constraints. This can cause the agent to invoke the external endpoint in overly broad contexts, increasing the chance of unnecessary data exposure, unintended spending through per-call billing, and unreviewed interaction with a third-party service.

VirusTotal

50/50 vendors flagged this skill as clean.