Skill Publish

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: skill-publish Version: 1.0.0 The skill's primary function is to safely publish other skills, with strong emphasis on sanitization and user approval. However, the `verify.md` file instructs the agent to execute `npx clawhub publish` and `npx clawhub install` commands, which accept user-controlled parameters like `--slug` and `--name`. If the OpenClaw agent does not rigorously sanitize these user-provided strings before executing the shell command, it could lead to a command injection vulnerability (RCE). While the skill's instructions do not explicitly encourage malicious behavior, this potential for RCE via unsanitized input makes it suspicious.

Findings (0)

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.

What this means

If the user approves the wrong folder, slug, or metadata, content could be published publicly.

Why it was flagged

The skill documents a high-impact publish command, but it is directly tied to the skill purpose and explicitly gated on user approval.

Skill content
Only after approval: npx clawhub publish <folder> --slug "<slug>" --name "<name>" --version "<version>"
Recommendation

Inspect the publish folder and confirm slug, name, version, description, and file list before approving the publish step.

What this means

Running the command may execute the current ClawHub CLI package available to npx.

Why it was flagged

The documented workflow invokes the ClawHub CLI through npx without pinning a package version; this is expected for the publishing workflow but depends on trusted package tooling.

Skill content
npx clawhub publish <folder>
Recommendation

Use a trusted environment and consider pinning or verifying the ClawHub CLI version if reproducibility or supply-chain control matters.

NoteHigh Confidence
ASI08: Cascading Failures
What this means

Accidentally published private data or incorrect content may require a new version or support intervention to remediate.

Why it was flagged

The artifacts acknowledge that published skills can persist publicly, so a mistake in sanitization or approval may have lasting impact.

Skill content
**Run this BEFORE any publish.** Public skills are permanent.
Recommendation

Treat the pre-publish review as the final checkpoint and verify that secrets, personal data, and internal references have been removed.