tone-rewriter

• Analyzed: May 11, 2026, 4:51 AM
• Findings: 0
• Version: 1.0.0
• Hash: d799d10df1c434b5ba76c7c3b21a5752eb091882b49e6f533bff9dd037f16b35
• Source: palm
• External report: View on VirusTotal

Overview

Type: OpenClaw Skill Name: tone-rewriter Version: 1.0.0 The skill instructs the AI agent to perform a global `npm install -g awal@2.0.3` and then `awal auth login` in `SKILL.md`. Global package installation is a high-privilege operation that introduces a significant supply chain vulnerability, as a compromised `awal` package could lead to arbitrary code execution on the host system. The `awal auth login` command also raises concerns about how an AI agent would securely handle authentication credentials. While the skill's core functionality involves making an external network request to `https://anicca-proxy-production.up.railway.app`, this request appears to send only the explicitly defined input data, showing no direct evidence of malicious data exfiltration from this skill bundle itself.

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.

ASI04: Agentic Supply Chain Vulnerabilities

Note

What this means

Installing a global CLI gives that package code execution during install/use, so users need to trust the package source.

Why it was flagged

The skill depends on a globally installed npm CLI and login flow that are not represented as an install spec. The version is pinned and the step is disclosed, so this is a supply-chain trust note rather than a concern.

Skill content

npm install -g awal@2.0.3
awal auth login

Recommendation

Verify the `awal` npm package and publisher before installing, and prefer an isolated environment if unsure.

ASI03: Identity and Privilege Abuse

Note

What this means

Using the skill can spend USDC from the configured x402/awal account.

Why it was flagged

The skill uses an authenticated payment flow for each request. This is clearly disclosed and aligned with the paid service, but it does involve account/payment authority.

Skill content

Pay $0.01 USDC per request via x402.

Recommendation

Confirm you are comfortable with the per-request charge and monitor usage if the agent may invoke the skill repeatedly.

ASI07: Insecure Inter-Agent Communication

Note

What this means

Text submitted for rewriting may be processed by the external service.

Why it was flagged

The documented workflow sends user-provided text to a third-party hosted endpoint. This is expected for a rewriting service, but the artifacts do not describe retention or privacy handling.

Skill content

Endpoint: `https://anicca-proxy-production.up.railway.app/api/x402/tone-rewriter`

Recommendation

Avoid submitting confidential, regulated, or sensitive personal text unless you trust the endpoint and its data handling.