audio-studio-mcp@1.1.1
CAUTION· not startedPublisher claims: "Local AI BGM and sound-effect generation (Stable Audio 3) as an MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso astral.sh, huggingface.co — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 3 scenarios · 0 deviationsStatic findings
<summary><b>"Intel Macs are not supported" on an Apple Silicon Mac?</b></summary> The environment was built with an x86_64 Python (for example an old Intel HomeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.curl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary><b>Parameter notes</b></summary> - **`audio_type`**: `music` / `instrument` / `sfx` / `raw`. The server adds the prefix the model was trained with (`TrFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct." own terminal (not in a chat), run this and paste the token:\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.curl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary><b>Share one server between sessions</b></summary> Each client session normally starts its own server process. Models load on the first call and are frFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Does it run on Windows, Linux or Intel Macs?</b></summary> **Windows:** yes, with an NVIDIA GPU. See [Quick start](#-quick-start). **Linux:** with aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.link.type, link.linkname = tarfile.SYMTYPE, "/etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.r = subprocess.run([exe, "-hide_banner", "-nostdin", "-y", *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen([sys.executable, str(TESTS / "fake_web_server.py"), "--web", str(port), "--no-browser"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-c", code], stdin=subprocess.DEVNULL,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…S), seamless loop, fades, then write 48 kHz/44.1 kHz WAV, OGG Vorbis or FLAC (+ .json sidecar). The input file is not modified. Steps run in that order. Does not load any model.""" …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.r = subprocess.run([sys.executable, "-c", code, str(path)], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary><b>Installer options</b></summary> | macOS | Windows | Effect | |---|---|---| | `--model all` | `-Model all` | Also download the small, fast `sm-music`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.out = subprocess.run(["/usr/sbin/sysctl", "-n", "sysctl.proc_translated"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."missing.wav", "reserved.wav", "", ".", "..", "secret.wav", "/etc/passwd", None, 3, ["a.wav"]]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.Popen([sys.executable, str(TESTS / "fake_web_server.py"), "--web", str(port), "--no-browser"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."notes.txt", "a.wav.json", "missing.wav", "/etc/passwd", "%2Fetc%2Fpasswd", "link.wav",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert r.json()["arguments"]["input_audio"] == str(out / "a.wav")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.assert r.json()["fields"][0]["field"] == "input_audio"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for audio-studio-mcp@1.1.1 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim kanaworksai-hue: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.