Most static findings are false positives caused by Markdown code fences and inline formatting. Confirmed risks are external package installation, third-party CLI execution, and transmission of prompts or search queries to remote services.
Image prompts and research queries are submitted to remote providers through belt. Sensitive product details or personal data could leave the local environment.
The commands explicitly pass prompt and query fields to named remote applications. The skill provides no warning against submitting sensitive information.
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 instructs users to run npx against an external package. Installation can execute third-party package lifecycle code and creates a supply-chain risk.
Most static findings are false positives caused by Markdown code fences and inline formatting. Confirmed risks are external package installation, third-party CLI execution, and transmission of prompts or search queries to remote services.
Image prompts and research queries are submitted to remote providers through belt. Sensitive product details or personal data could leave the local environment.
The commands explicitly pass prompt and query fields to named remote applications. The skill provides no warning against submitting sensitive information.
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 instructs users to run npx against an external package. Installation can execute third-party package lifecycle code and creates a supply-chain risk.
Most static findings are Markdown delimiters or inline formatting and do not execute commands. Six findings contain real npx or belt commands for installation, authentication, or hosted application requests. No malicious intent or prompt injection was found.
1
Files scanned
248
Lines analyzed
8
Review items
0
False positives ignored
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The line instructs users to run an npx command that installs third-party skill content. The backticks are Markdown, but the command is intended for execution.