ClawHub

ai phone call

Security checks across malware telemetry and agentic risk

Overview

This skill places AI-assisted outbound calls and stores call records, but those sensitive behaviors are disclosed, user-confirmed, and aligned with its stated purpose.

Install only if you are comfortable giving this skill an outbound-call API key and sending phone numbers plus call context to skill.black or your configured OUTBOUND_BASE_URL. Confirm every recipient and purpose before calling, avoid including unnecessary sensitive details, and delete the local memory/skills request and transcript logs when you no longer need them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The API reference enables outbound calling and retrieval of phone numbers and full chat logs, which are privacy-sensitive data, but it does not document consent requirements, data minimization, retention limits, or access controls for handling that information. In a skill context, this omission is risky because it can lead implementers to collect, transmit, and expose personal communications without adequate safeguards or user warning.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script stores sensitive call records locally, including phone numbers and full conversation logs, in plaintext JSONL files under the skill directory without explicit consent, retention controls, or access restrictions. This creates a privacy and data-exposure risk if the local machine, workspace, backups, or repository are accessed by other users or processes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal