Sms Alert

Security checks across malware telemetry and agentic risk

Overview

The skill is a plausible SMS Alert integration, but it gives broad authenticated API access that could change contacts, templates, alerts, or SMS-related data without clear approval boundaries.

Review this skill before use. It appears aligned with SMS Alert, but connect only an account you are comfortable delegating to an agent, and require confirmation before any action that sends SMS messages, modifies contacts or templates, or uses raw POST/PUT/PATCH/DELETE API requests.

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
Medium
What this means

An agent using this skill could potentially make broad changes to SMS Alert account data, such as contacts, templates, alerts, or SMS-related resources, if the user grants access.

Why it was flagged

This gives the agent a broad authenticated API escape hatch, including mutation and deletion methods, without clear limits or explicit user approval requirements for high-impact SMS Alert actions.

Skill content
When the available actions don't cover your use case, you can send requests directly to the SMS Alert API through Membrane's proxy... Common options: HTTP method (GET, POST, PUT, PATCH, DELETE).
Recommendation

Only use this skill with a Membrane/SMS Alert account whose permissions are appropriate, and require explicit user confirmation before sending messages, bulk-changing contacts, or running POST/PUT/PATCH/DELETE proxy requests.

#
ASI03: Identity and Privilege Abuse
Low
What this means

The agent may be able to use the connected SMS Alert account until access is revoked or the connection is removed.

Why it was flagged

The skill uses delegated authentication and credential refresh for Membrane/SMS Alert. This is expected for the integration, but it gives the skill access to act through the connected account.

Skill content
Membrane handles authentication and credentials refresh automatically... Use `membrane connection ensure`... The user completes authentication in the browser.
Recommendation

Connect the least-privileged SMS Alert account available, review the Membrane connection permissions, and revoke the connection when no longer needed.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

The behavior depends on whatever version of the Membrane CLI npm serves at install time.

Why it was flagged

The skill instructs installation of an external CLI using the latest npm package. This is purpose-aligned, but it means the installed code is not pinned to a reviewed version in the artifact.

Skill content
npm install -g @membranehq/cli@latest
Recommendation

Install the CLI from the official package source, consider pinning a known version, and avoid running global installs in highly sensitive environments without review.