Back to skill

Security audit

Cal Com Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Cal.com automation guide whose sensitive actions are visible and aligned with scheduling administration.

Install this only if you intend to let an agent operate your Cal.com account through Rube MCP. Review actions before creating bookings, teams, or changing webhooks, and only point webhooks at HTTPS endpoints you control or trust because booking-event data may be delivered there.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The webhook guidance instructs users how to configure external subscriber URLs but does not warn that booking events and related metadata will be transmitted to third-party endpoints. In a scheduling context, webhook payloads may contain personal or sensitive business information, so omission of this warning can lead to unintended data disclosure to external systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents webhook deletion as a routine operation without clearly warning that deletion is destructive and may permanently stop downstream automations, notifications, or audit-relevant integrations. In operational environments, a user or agent following these instructions could unintentionally disrupt business workflows or incident monitoring.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description scopes the skill to managing bookings, checking availability, configuring webhooks, and handling teams. However, the file also defines a separate 'Organization Management' workflow using CAL_GET_ORGANIZATION_ID, which extends beyond the enumerated capabilities in the description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.