intent-router

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

Overview

This instruction-only skill coherently calls a disclosed paid intent-classification API, but users should notice the npm CLI install, x402 login/payment, and third-party data transfer.

Before installing, confirm that you trust the `awal` npm package and the hosted classifier endpoint, and set payment limits or require review if the agent might invoke this skill repeatedly. Avoid sending sensitive text unless the service's privacy practices are acceptable to you.

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.

What this means

Installing the CLI can change the local environment and introduces trust in the npm package.

Why it was flagged

The skill instructs installation of a global npm CLI package. The version is pinned and the package is central to the stated x402 workflow, but it is still a third-party dependency users should verify.

Skill content
npm install -g awal@2.0.3
awal auth login
Recommendation

Verify the `awal` package source before installing, consider avoiding global installation where possible, and keep the pinned version under review.

What this means

If used frequently or automatically, the skill could incur small repeated charges.

Why it was flagged

The skill uses an authenticated x402 payment flow and discloses a per-request USDC cost. This is purpose-aligned, but it gives the workflow access to a payment-capable account.

Skill content
awal auth login ... x402 pay ... $0.005 USDC per request (Base network)
Recommendation

Use a wallet/account with spending limits, review any payment prompts, and avoid enabling unattended high-volume use unless the cost is acceptable.

What this means

Messages submitted for classification may be visible to or processed by the external service.

Why it was flagged

The usage example sends the text to classify and the candidate intents to an external hosted endpoint. This data flow is expected for the skill's purpose, but it means user text leaves the local environment.

Skill content
https://anicca-proxy-production.up.railway.app/api/x402/intent-router ... -d '{"text":"I want to book a flight to Tokyo next week","intents":[...]}
Recommendation

Do not send sensitive or regulated text unless you trust the service and understand its privacy and retention practices.