TelCall Twilio

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is clearly meant to make Twilio phone calls, but its call script places the message directly into Twilio XML, which could let crafted message text alter call behavior.

Install only if you are comfortable giving this skill Twilio call authority and storing a Twilio Auth Token locally. Before use, the script should be updated to escape message text before inserting it into TwiML, and you should monitor Twilio usage and costs.

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.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

A crafted or untrusted alert message could cause an unexpected Twilio call flow, call failure, or extra account charges instead of only reading the message aloud.

Why it was flagged

The message argument is inserted directly into Twilio's TwiML XML without escaping. If the message includes XML/TwiML markup, it could break the intended spoken-message behavior or alter the call instructions.

Skill content
MESSAGE="$1"
TWIML="<Response><Say language=\"en-US\" voice=\"alice\">Emergency notification: ${MESSAGE}</Say></Response>"
Recommendation

Escape XML special characters before placing the message inside TwiML, or use a safer Twilio workflow that treats the message strictly as text. Consider confirming before placing paid calls.

What this means

Anyone or any process with access to this local config file under the same user account could potentially use the Twilio credentials to place calls or access the Twilio account API.

Why it was flagged

The setup script collects and stores a Twilio Auth Token locally so the skill can place calls through the user's Twilio account.

Skill content
read -p "Auth Token: " auth_token
cat > "$CONFIG_FILE" << EOF
{
    "account_sid": "$account_sid",
    "auth_token": "$auth_token"
Recommendation

Use a minimally privileged Twilio token if possible, protect the OpenClaw workspace, rotate the token if it may have been exposed, and consider changing the prompt to hide token entry with silent input.

What this means

Users have less external provenance information for deciding whether to trust the skill author and future updates.

Why it was flagged

The registry metadata does not provide a source repository or homepage for provenance verification, although the supplied artifacts include the full scripts.

Skill content
Source: unknown
Homepage: none
Recommendation

Review the included scripts before use and prefer installing from a skill with a verifiable source repository or trusted publisher history.