Skills/ClawHub/muse-ai

muse-ai@1.0.6

CAUTION· install only

Publisher claims: "AI 音乐创作助手 — 通过对话生成原创歌曲、纯音乐和 BGM。 当用户想要创作、生成、制作任何形式的音乐时使用此技能。 包括:生成带人声的歌曲、写歌词、作曲编曲、制作纯音乐/BGM/配乐,或将文字变成歌曲。 当用户提到具体音乐风格(如"来首民谣""做首说唱")时也应触发。 支持三种模式:灵感模式(一句话生成)、..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher a64307410 · publishing for 239 daysInstalls 1,194Last detonated 27 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.2sfilesystemwrote ~/.muse/device_id
0.2sprocessexec /usr/bin/dirname
0.2sprocessexec /usr/bin/cut
0.2sprocessexec /usr/bin/mkdir
0.2sprocessexec /usr/bin/basename
0.2sprocessexec /usr/bin/cp
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: muse_api.py: error: the following arguments are required: command
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1:
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: register.py: error: the following arguments are required: command
0.4sprocess3 of 3 bundled scripts run with no arguments
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.5sprocesssecond launch, clock +45 days, CI unset
0.7sfilesystemread ~/.muse/device_id outside project
0.7sprocessexec /usr/bin/dirname
0.7sprocessexec /usr/bin/tr
0.7sprocessexec /usr/bin/cut
0.7sprocessexec /usr/bin/mkdir
0.7sprocessexec /usr/bin/rm
0.7sprocessexec /usr/bin/basename
0.7sprocessexec /usr/bin/cp

Static findings

MEDIUM
URL with suspicious TLDscripts/muse_api.py:340 · URL with suspicious TLD — commonly used for phishing/malware_print_json({"url": f"https://skills.muse.top/?did={device_id}", "deviceId": device_id})Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:596 · URL with suspicious TLD — commonly used for phishing/malware- 链接:使用 Step 0 中生成的 `REGISTER_URL`(`https://skills.muse.top/?did=${DEVICE_ID}`)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/muse_api.py:14 · URL with suspicious TLD — commonly used for phishing/malwareBASE_URL = "https://skill-api.muse.top"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commandinstall.sh:178 · Privileged sudo command — agent may execute with elevated privilegesecho " Ubuntu/Debian: sudo apt install python3"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL with suspicious TLDpackage.json:29 · URL with suspicious TLD — commonly used for phishing/malware"homepage": "https://skills.muse.top"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commandinstall.sh:188 · Privileged sudo command — agent may execute with elevated privilegesecho " Ubuntu/Debian: sudo apt install python3"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,207 tok
1 file · 10 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim a64307410: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. URL with suspicious TLD≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim a64307410Propose a patch to the maintainer