music-craft@1.8.0
VERIFIED· install onlyPublisher claims: "Generate songs, instrumentals, or lyrics-driven tracks through a structured OpenClaw-native workflow with anti-sparse prompt engineering and quality verification. Provider-agnostic — works with any music backend the runtime exposes (ACE-Step, MusicGen, Stable Audio, or a cloud CLI). Includes local helpers for a loopback ACE-Step server (submit, wait, duration check, cache recovery), lyrics linting, and optional stem separation (Demucs) and stem remixing (ffmpeg) of the user's own local audio files." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
return subprocess.run(command, text=True).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…`scripts/extract_stems.py` | a local audio file you pass | stem files and `stems.json` in the output folder you choose | none (Demucs may download its own model weights on first us…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."[Bridge]", "[Outro]", "[Break]", "[Inst]", "[Solo]",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.It does not kill jobs; it reports timeout with the best known state.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.-F "prompt=<prompt>" \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.---Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.| `[Inst]` | Pure instrumental section, no vocals |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.`[mm:ss.xx][Inst]` instead of forcing a timestamp.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
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.