🎼 ACE Step — Pro Pack on RunComfy

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent RunComfy music-generation skill, but it uses a RunComfy account token, runs an external CLI, and may send lyrics or audio to RunComfy for paid processing.

This skill appears benign and purpose-aligned. Before installing or using it, verify the RunComfy CLI source, protect your RUNCOMFY_TOKEN, review the endpoint and duration because usage is paid, and avoid sending private audio or lyrics unless you are comfortable with RunComfy handling them.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#ASI02: Tool Misuse and Exploitation

Low

What this means

The agent may invoke a paid remote generation workflow and create local output files when the user asks for music generation or editing.

Why it was flagged

The skill instructs use of the runcomfy CLI to submit generation jobs and write outputs. This is central to the stated purpose, but users should review cost-bearing runs and output paths.

Skill content

runcomfy run acestep-ai/ace-step/text-to-audio \
  --input '{"tags": "..."}' \
  --output-dir ./out

Recommendation

Confirm the requested duration, endpoint, and output directory before running; avoid unattended batch use unless the cost and scope are clear.

#ASI03: Identity and Privilege Abuse

Low

What this means

Anyone or any agent process with access to the token/config may be able to use the RunComfy account and incur usage costs.

Why it was flagged

The skill requires a RunComfy token and config directory. This is expected for the integration, but it means actions are authenticated to the user's RunComfy account.

Skill content

clawdis:
  requires:
    bins:
      - runcomfy
    env:
      - RUNCOMFY_TOKEN
    config:
      - ~/.config/runcomfy

Recommendation

Keep RUNCOMFY_TOKEN private, use the least-privileged token available, monitor account usage, and revoke or rotate the token if it is no longer needed.

#ASI04: Agentic Supply Chain Vulnerabilities

Low

What this means

Installing or running the latest npm package places trust in the published @runcomfy/cli package and, for global install, changes the local environment.

Why it was flagged

The documented setup uses npm/npx to install or run an external CLI without a pinned version. This is normal for a CLI-based integration, but it relies on the external package source.

Skill content

npm i -g @runcomfy/cli                              # global install
npx -y @runcomfy/cli --version                      # zero-install

Recommendation

Install the CLI from the official package source, consider pinning a known-good version, and avoid running npm/npx commands from untrusted contexts.

#ASI07: Insecure Inter-Agent Communication

Low

What this means

Prompts, lyrics, and selected audio may be sent to RunComfy for processing.

Why it was flagged

The skill sends generation/editing requests through RunComfy. For text-to-audio this includes prompts and lyrics; for inpaint/outpaint workflows it may involve user-selected audio.

Skill content

Generate, inpaint, and outpaint music with ACE Step on RunComfy via
  the `runcomfy` CLI

Recommendation

Do not submit confidential lyrics, private audio, or third-party material unless you are comfortable with RunComfy processing it under its terms.