ClawHub
Back to skill

Security audit

call4me

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps an agent place user-approved business phone calls through call4me, with disclosed remote MCP use and no local executable code.

Before installing, understand that call4me requires a remote account, prepaid credits, and browser sign-in, and that it may save personal profile details to place calls. Only provide fields needed for the call, decline optional details you do not want stored, and confirm the business and request before any call is placed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
# call4me

[Website: call4me](https://call4.me) · [MCP setup](https://call4.me/mcp) · [Source skill](https://github.com/skeptrunedev/call4me/blob/main/chatgpt-plugin/skills/get-started/SKILL.md)

Your AI agent phones businesses for you: books, reschedules, cancels, asks, and waits on hold.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The workflow explicitly instructs the agent to collect and persist sensitive personal data including full name, phone, email, home address, and potentially car details, but the skill description does not present a clear privacy notice, data handling explanation, retention policy, or consent language. In a voice-calling context this increases risk because users may disclose more information than is necessary without understanding how it will be stored or used by the remote service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.