phone calling

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: phone-calling Version: 1.0.7 The OpenClaw AgentSkills skill bundle provides a comprehensive API for an AI agent to make international phone calls, manage sessions, and access call-related features like transcription and sentiment analysis. All documented API endpoints and instructions are clearly aligned with the stated purpose of a phone calling service. There is no evidence of intentional harmful behavior, data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the AI agent in any of the provided files (SKILL.md, openapi.json, ringez-api-spec.md, ringez-implementation-guide.md, ringez-quickstart-guide.md). The skill explicitly directs users to a website for adding credits, avoiding direct handling of payment information within the agent environment.

Findings (0)

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 the agent has a valid session, it could place calls to third parties and spend calling minutes in ways the user did not specifically approve.

Why it was flagged

The skill exposes real-world phone call initiation, including direct automated calling by agents, without artifact-backed instructions requiring per-call user approval, recipient confirmation, spend limits, or duration limits.

Skill content
Direct Mode ... Best for: AI agents, automated calls ... POST /api/v1/calls/initiate ... { "to_number": "+919876543210", "mode": "direct" }
Recommendation

Require explicit confirmation before every call, showing the destination number, mode, purpose, expected cost, and maximum duration; prefer bridge mode and keep idempotency keys enabled.

What this means

Users may not realize the agent will handle credentials or session tokens that can authorize paid calls and account access.

Why it was flagged

The session ID functions as an account credential for balance checks and call initiation, while the registry requirements declare no primary credential or required environment variable.

Skill content
Login with password ... Save the `session_id` — you will need it for all API calls.
Recommendation

Declare the credential/session requirements clearly, store session IDs only in approved secret storage, and let users revoke or rotate sessions easily.

What this means

Phone numbers, call events, and transcribed conversation content could be sent to external agent/webhook systems without users fully understanding the privacy implications.

Why it was flagged

The API documentation supports sending call status and transcription events to webhook endpoints, but the artifacts do not clearly define data boundaries, recipient consent, or retention for call content and metadata.

Skill content
"transcribe": true ... "webhook_url": "https://agent.example.com/webhooks/call-status" ... "events": ["call.initiated", "call.ringing", "call.answered", "call.completed", "call.failed", "transcription.updated", "balance.low"]
Recommendation

Use webhooks and transcription only when necessary, disclose who receives the data, verify webhook signatures, and obtain consent where required by law or policy.

What this means

Users may trust the skill more than they should and overlook the account, billing, and call-data exposure involved in using it.

Why it was flagged

The privacy/authentication messaging is internally inconsistent and can understate that the service handles credentials, phone numbers, call metadata, and possibly transcripts.

Skill content
enables autonomous calling capabilities with privacy-first design ... without requiring authentication or personal data. ... Authentication: API Key-based (bearer token)
Recommendation

Clarify the privacy model, authentication model, data collected, third-party processors, and any recording/transcription behavior before users grant access.

What this means

Using the optional SDKs adds package supply-chain trust outside the reviewed instruction-only skill.

Why it was flagged

The guide suggests optional SDK installation from package registries, but the skill itself has no install spec, lockfile, or bundled code for review.

Skill content
pip install ringez-sdk ... npm install @ringez/sdk
Recommendation

Verify package ownership, versions, and integrity before installing any SDK, or use the documented REST API directly.