Lunara Voice

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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

A simple request to call someone can trigger a real phone call, repeated background polling, transcript retrieval, analytics saving, and tagging before the user gets another response.

Why it was flagged

The skill forces a fixed tool sequence and silent polling for any outbound-call request, rather than requiring an explicit confirmation point or letting the user control the stop conditions.

Skill content
AUTONOMOUS EXECUTION ... Whenever the user asks to call someone ... you MUST complete ALL steps below in ONE turn ... Do NOT message the user — poll silently.
Recommendation

Require explicit user confirmation before placing calls or campaigns, and let users choose whether to poll, analyze, tag, or retrieve transcripts afterward.

What this means

A mistaken or overly broad instruction could start calls to many recipients, affecting costs, compliance, and recipient privacy.

Why it was flagged

The tools can initiate bulk outbound calling at large scale, but the artifacts do not describe approval gates, contact validation, rate limits, or safe defaults for campaign execution.

Skill content
`lunara_campaign_create` — Create a call campaign with contacts ... `lunara_campaign_start` — Start a campaign's call loop ... Max contacts per campaign: 10,000
Recommendation

Add explicit confirmation for every outbound call and campaign start, show contact counts before execution, and define safe limits and cancellation steps.

What this means

The agent may be able to create, list, revoke, or permanently delete Lunara API keys for the configured account.

Why it was flagged

The plugin uses configured account identity information to administer API keys, including irreversible deletion. This is high-impact account authority.

Skill content
`X-User-Email`: cfg.userEmail ... `lunara_key_create` ... `lunara_key_revoke` ... `lunara_key_delete` ... `Permanently delete a Lunara API key. This action cannot be undone.`
Recommendation

Use a least-privilege API key, avoid enabling key-management functions unless needed, and require explicit confirmation before creating, revoking, or deleting credentials.

What this means

Private call content and personal data can be brought into the agent conversation or exported for training workflows.

Why it was flagged

The plugin can retrieve and export call transcripts, including raw unmasked data when requested. This is purpose-aligned, but transcripts may contain sensitive personal or business information.

Skill content
`lunara_history_detail` | Get full call detail + transcript + tags ... `lunara_export_bulk` | Bulk export conversations for LLM training ... Set mask_pii=false to get raw data.
Recommendation

Keep PII masking enabled by default, export only selected conversations, and avoid sharing raw transcripts unless necessary.

What this means

Call and campaign event data may be sent to external webhook endpoints after setup.

Why it was flagged

Webhook subscriptions are an expected integration feature, but they create persistent outbound event flows to configured URLs.

Skill content
`lunara_webhook_create` | Create webhook for real-time call event notifications ... Webhook events: call.started, call.completed, call.failed, analysis.completed, campaign.started, campaign.completed, campaign.failed
Recommendation

Create webhooks only for trusted HTTPS endpoints, review subscribed event types, and remove unused webhook subscriptions.