ClawHub
Back to skill

Security audit

Calendar Reminder Paid

Security checks for vulnerabilities and agentic risk

Overview

This calendar reminder skill is broadly coherent with its stated purpose, but users should understand that calendar details may be sent to notification channels and written to local reports.

Before installing, verify which calendars are connected, who receives Feishu or Telegram notifications, whether personal calendar entries are included, and where CSV reports are stored or retained. Use separate consent for team calendars and avoid enabling admin summaries for sensitive personal schedules unless that is intentional.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends calendar contents to external channels such as Feishu and Telegram and to admin recipients, but the description does not clearly warn users that meeting titles, times, locations, and analysis outputs may leave the original calendar system. In a calendar skill, this is security-relevant because users may expose sensitive business or personal schedule data without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The weekly analysis flow exports detailed calendar data into a local CSV containing dates, times, titles, categories, and locations, but the skill does not prominently warn users about this secondary storage. Local file export increases exposure through filesystem access, backups, sync tools, and accidental sharing, especially on shared workstations or managed endpoints.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation claims team sync only reads busy/free status, but the skill examples elsewhere process and transmit full event details including titles, times, locations, and owner identifiers to admins and notification channels. This mismatch can cause operators and users to authorize the skill under a false privacy assumption, leading to unintended disclosure of calendar contents.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The examples and setup hard-code the timezone to Asia/Shanghai, including event retrieval and cron registration, which reflects a locale assumption in the skill's natural-language behavior. The file does not clearly present this as a required regional constraint or offer user opt-in/selection as the default behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.