ClawHub
Back to skill

Security audit

RingBot

Security checks for vulnerabilities and agentic risk

Overview

RingBot is a disclosed outbound-calling skill, but it gives an agent broad real-world calling capability without enough consent, privacy, or confirmation boundaries.

Install only if you are prepared to manage explicit consent and compliance for every outbound call. Require confirmation of the phone number, call purpose, caller identity, and any sensitive context before calls are placed, and avoid bulk lead, patient, reminder, or recurring-call workflows unless you have clear authorization and appropriate legal/privacy controls.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation promotes AI-initiated phone calls, appointment reminders, lead qualification, and personal/business outreach without warning about consent, call recording, identity disclosure, or privacy/legal obligations. Because the skill handles phone numbers, call objectives, and potentially sensitive context, omitting these warnings increases the risk of unlawful or non-consensual calling, social engineering misuse, and disclosure of personal or regulated information.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

  • Get: GROQ_API_KEY
bash
# .env for DIY setup
TWILIO_ACCOUNT_SID=your_sid
TWILIO_AUTH_TOKEN=your_token
TWILIO_PHONE_NUMBER=+1234567890

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is overly broad for a high-impact capability: words like "call," "phone," "dial," and "ring" can appear in ordinary conversation and may cause unintended activation of a skill that can place real outbound calls. In this context, accidental invocation is especially dangerous because it can disclose private user data, contact third parties without clear consent, or initiate chargeable actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

Making a Call

bash
curl -X POST http://localhost:8000/ringbot/call \
  -H "Content-Type: application/json" \
  -d '{
    "to": "+1XXXXXXXXXX",