ClawHub
Back to skill

Security audit

BGM Maker

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward SenseAudio music-generation helper, with expected third-party API use but no hidden or destructive behavior found.

Install only if you are comfortable sending video scene and style descriptions to SenseAudio using a revocable API key. Avoid confidential prompt details, expect the default workflow to create three generation jobs per request, and verify SenseAudio licensing before relying on commercial-use claims.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
for i in 1 2 3; do
  RESP=$(curl -s -X POST "https://api.senseaudio.cn/v1/song/music/create" \
    -H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
Confidence
88% confidence
Finding
The skill sends user-derived style text to an external third-party API along with authentication credentials, which is a genuine external data transmission path. In context this is expected for a music-generation skill, but it still creates privacy and governance risk because user content is transferred off-platform and the skill does not specify consent, minimization, or restrictions on sensitive input.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
for i in 1 2 3; do
  RESP=$(curl -s -X POST "https://api.senseaudio.cn/v1/song/music/create" \
    -H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
Confidence
88% confidence
Finding
The skill sends user-derived style text to an external third-party API along with authentication credentials, which is a genuine external data transmission path. In context this is expected for a music-generation skill, but it still creates privacy and governance risk because user content is transferred off-platform and the skill does not specify consent, minimization, or restrictions on sensitive input.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.