Huo15 Comic Bgm

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  0.1.0

Overview

The skill does what it claims by generating background music with a paid Suno API, but it has documentation gaps and bundles unused media helper code.

Install only if you intend to use a paid Suno-compatible service and are comfortable sending generated mood-based prompts to api.sunoapi.org. Set SUNO_API_KEY deliberately, run it only on script files and output paths you choose, and treat the bundled Ark helper as extra unused surface unless you separately trust those APIs.

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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill documentation describes capabilities that imply file read/write, environment access, and network use via a Python script and Suno integration, but no explicit permissions are declared. This creates a transparency and policy-enforcement gap: users or orchestrators may invoke the skill without understanding that it can access local files, write outputs, or make outbound requests, increasing the chance of unintended data exposure or unsafe execution context.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger terms are broad generic phrases for music generation, with no boundary conditions or exclusions, so the skill may activate in contexts where the user did not intend to call it. In an agent system, overbroad triggering can cause unintended network calls, file operations, or media generation costs, especially because this skill can invoke external services and write output files.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The helper automatically reads local image files and converts them to data URIs for submission to a remote API, which can exfiltrate local file contents if higher-level code passes sensitive paths. In a BGM-focused skill, this capability is especially suspicious because local image upload is not needed for the stated function, so the mismatch increases the privacy risk.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The TTS method transmits arbitrary input text to an external service and writes returned audio to disk without any visible consent, redaction, or sensitivity checks. If scripts or prompts contain private or proprietary content, this creates a real data exposure risk; in a BGM-only skill, TTS is also outside expected scope and therefore less justifiable.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill transmits user-derived prompt content and an API credential to a third-party service without any user-facing disclosure or consent mechanism in this file. In an agent context, this can create privacy and compliance issues because script content may contain sensitive material and operators may not realize external processing occurs.

VirusTotal

65/65 vendors flagged this skill as clean.