Voipms Sms

PassAudited by ClawScan on May 10, 2026.

Overview

This skill appears to do what it says—send and retrieve VoIP.ms SMS—but it needs VoIP.ms credentials and can send or display real text messages.

This skill is coherent and limited to VoIP.ms SMS operations. Before installing, create a dedicated VoIP.ms API account with only SMS permissions, store its credentials carefully, and require confirmation before sending messages. When retrieving messages, limit the DID and date range because SMS contents may be sensitive.

Findings (3)

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 invoked with the wrong recipient or message, it could send an unintended SMS from the user's VoIP.ms number.

Why it was flagged

The tool can send SMS messages to a supplied destination using the user's VoIP.ms account. This is the stated purpose, but it is an external action that may contact real people or incur costs.

Skill content
"method": "sendSMS", "did": args.did, "dst": args.dst, "message": args.message
Recommendation

Use the send function only after confirming the source number, destination number, and message text. Consider requiring explicit user approval before any send.

What this means

Anyone or any agent process with access to those environment variables could use the VoIP.ms SMS API within the credential's permissions.

Why it was flagged

The skill requires VoIP.ms API credentials. This is expected for the integration, and the documentation also recommends a dedicated SMS-only API account.

Skill content
export VOIPMS_API_USERNAME="my_api_username"; export VOIPMS_API_PASSWORD="my_api_password"
Recommendation

Follow the skill's advice: use a dedicated VoIP.ms sub-account/API credential limited to SMS permissions, avoid main admin credentials, and rotate the credential if exposed.

What this means

Private SMS contents may appear in the conversation or logs, and malicious message text should not be treated as instructions.

Why it was flagged

Retrieved SMS messages are printed into the tool output, where they may become visible to the agent/user context. SMS content can be private and may also contain untrusted instructions from message senders.

Skill content
"method": "getSMS" ... print(json.dumps(parsed, indent=2))
Recommendation

Fetch only the needed DID and date range, avoid retrieving sensitive conversations unnecessarily, and treat SMS message bodies as untrusted data.