Security audit
Cal.com
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Cal.com integration that can make real scheduling changes and create persistent automations, but its risky actions are purpose-aligned and clearly gated on user approval.
Install this only if you intend to connect Cal.com through Maton. Review OAuth scopes, approve each write or automation separately, and treat webhooks, trigger destinations, and hosted functions as persistent data flows that may expose attendee names, emails, meeting details, and other business data until removed.
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
- 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
Static analysis
No suspicious patterns detected.