Security audit

Claw Calendar

Security checks for vulnerabilities and agentic risk

Overview

This calendar skill is coherent and not malicious, but it gives an assistant API-key access to create, update, and delete calendar data without enough confirmation or privacy guidance.

Review before installing. Use this only with a calendar service and API key you trust, prefer a scoped or revocable API key if available, and require the assistant to show the exact calendar/event details and get your confirmation before any delete operation.

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
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Tool Parameter Abuse

High

Category: Tool Misuse
Content: ### Delete Event ``` DELETE /api/calendars/{calendarId}/events/{eventId} Headers: X-API-Key: ${CALENDAR_API_KEY} ```
Confidence: 97% confidence
Finding: The exposed DELETE endpoint allows direct destructive action using model-controlled parameters such as calendarId and eventId, creating a tool-parameter abuse risk. If the agent misresolves identifiers, follows a malicious prompt, or acts on incomplete context, it could delete arbitrary events without adequate user intent verification.

Tool Parameter Abuse

High

Category: Tool Misuse
Content: ### Delete Calendar ``` DELETE /api/calendars/{calendarId} Headers: X-API-Key: ${CALENDAR_API_KEY} ```
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High

Category: Tool Misuse
Content: ### Delete Event ``` DELETE /api/calendars/{calendarId}/events/{eventId} Headers: X-API-Key: ${CALENDAR_API_KEY} ```
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill instructs the agent to send calendar contents and event details to an external API but provides no privacy notice, consent guidance, or data-handling warning. Calendar data often contains sensitive personal or business information, so silent transmission to a third-party service increases the risk of unintended disclosure.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill documents a destructive delete operation for calendar events without requiring an explicit confirmation step or warning the user before execution. In an agent setting, ambiguous or manipulated prompts could cause irreversible deletion of calendar data, especially because event/calendar IDs may be selected automatically by the assistant.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: This markdown file documents DELETE operations for calendars without any warning that the action removes user data or may be irreversible. Under the markdown-specific missing-warning rule, descriptions of behaviors that affect user data should disclose the impact on data integrity.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The Delete Event section documents a data-destructive operation but does not warn users that event data will be removed or explain any limits of the mentioned potential undo functionality. For markdown skill documentation, destructive behaviors affecting user data should include a clear warning.

Static analysis

No suspicious patterns detected.