Security audit

日历管理技能基础版

Security checks for vulnerabilities and agentic risk

Overview

This calendar skill is mostly a CLI wrapper, but its description, triggers, and privacy claims are materially inconsistent with what it actually does.

Review this skill carefully before installing. Use it only for calendar operations, confirm any create/update/delete action before execution, and do not rely on its claims about security scanning or local-only data handling. Expect calendar data and credentials to interact with external providers through porteden, Google, or Outlook services.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (5)

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The manifest description advertises security detection, compliance audit, vulnerability scanning, and encryption protection capabilities, but the body of the skill only documents calendar CRUD operations through a CLI. This mismatch can cause an agent or user to invoke the skill in inappropriate high-trust security contexts, leading to unsafe reliance on a tool that does not provide the claimed protections.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The trigger conditions claim suitability for data analysis, report generation, statistical insights, and visualization, which are not supported by the documented commands or examples. Overbroad activation criteria increase the chance that an agent will select this skill for unrelated tasks and then perform unintended exec-backed operations in the wrong context.

Intent-Code Divergence

High

Confidence: 99% confidence
Finding: The skill states that all FREE-version data is stored locally and not uploaded to the cloud, yet it explicitly requires network access and interacts with Google/Outlook calendar APIs. This is a materially false security claim that may cause users to expose sensitive calendar contents under incorrect assumptions about data locality and third-party transmission.

Vague Triggers

High

Confidence: 94% confidence
Finding: The skill's trigger conditions are overly broad and disconnected from its actual function as a calendar-management wrapper. In an agent environment, broad triggers can cause inappropriate auto-selection of an exec-capable skill, increasing the risk of accidental command execution, data access, or modification in response to unrelated requests.

Vague Triggers

High

Confidence: 97% confidence
Finding: The description uses vague activation language spanning unrelated security and compliance tasks, which is especially risky because the skill is allowed to use exec and write-capable tooling. In this context, misleading scope statements can route sensitive security workflows to a tool that neither performs those functions nor enforces the safeguards users would expect.

Static analysis

No suspicious patterns detected.