ClawHub
Back to skill

Security audit

calendar-subscribe

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it says: turn a timetable into a shareable calendar file and simple subscription page.

Before installing, be aware that generated ICS files and hosted landing pages can reveal schedule details to anyone with the public URL. Use a dedicated output directory, review the generated calendar before publishing, and only apply the nginx/hosting example on infrastructure you control.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to generate artifacts such as an ICS file, landing page, and QR/poster assets, which implies file creation or modification, yet it declares no tool scope or permissions boundary. In an agent environment, undeclared write capability increases the chance of over-privileged execution, unintended file modification, or writing sensitive/generated content to unsafe locations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases like 'share calendar with classmates' and generic terms such as 'calendar subscription' or 'webcal', which can match common user requests beyond the narrow timetable-to-ICS use case. Over-broad activation can cause the wrong skill to run, leading to unintended file handling, hosting guidance, or exposure of user data in contexts where a safer or more appropriate skill should have been used.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The document declares lang="zh-CN" and all visible user-facing text is in Simplified Chinese, with no indication that other languages are supported or that the Chinese-only experience is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.