muse-ai
What this skill does
AI 音乐创作助手 - 通过对话生成原创歌曲、纯音乐和 BGM
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=muse-aiAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/muse_api.py
The script sends data to 'https://skill-api.muse.top' without clear user consent or transparency about what data is being sent.Privacy Concerns
Privacy Concerns via local-llm-review
scripts/muse_api.py
The script generates a device ID using a combination of hostname, MAC address, and username, hashes it with SHA256, and stores it locally. While this is not directly exfiltrating data, it raises privaAuthentication Risks
Authentication Risks via local-llm-review
scripts/register.py
The script includes a phone number validation and login process, but it does not clearly document how user credentials are stored or transmitted, raising potential concerns about authentication securiBadge
Add the Anomity scan badge for muse-ai to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of muse-ai? Report an issue or request a rescan.
