Security audit

Calendar Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language calendar helper that stores local calendar data and has no evidence of hidden access, exfiltration, or unsafe installation behavior.

Install this only if you want a Chinese-language local calendar helper. It writes calendar data locally and can permanently delete stored events when asked with an event ID, so review commands before using it for important schedule data.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (7)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README uses very broad natural-language example phrases such as asking about today's schedule or setting a reminder, but it does not define clear invocation or activation boundaries for when the skill should engage. In an agent ecosystem, this can cause unintended triggering during ordinary conversation, leading to surprise actions like creating reminders or exposing calendar data without explicit user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: All headings, trigger rules, examples, and operational descriptions are written exclusively in Chinese, with no indication that users may interact in another language or opt into this locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the regional constraint is explicitly justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad, common terms for everyday scheduling conversations, so the skill may activate when the user did not explicitly intend to invoke a calendar tool. In a skill that can modify stored data and schedule reminders, unintended activation can lead to accidental event creation, modification, or deletion based on ambiguous natural-language input.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises delete capability and persistent file-backed storage, but it does not specify explicit user warning, consent, or confirmation before modifying or removing data. Because calendar entries are persisted under a workspace path, mistaken or ambiguous commands could cause durable loss or corruption of user schedule information.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The module description, command parsing, help text, and examples are all written specifically for Chinese-language inputs such as "添加", "今天", and "删除", with no indication that users may choose another language. This creates a locale/language restriction in the skill's natural-language interface without explicit opt-in or justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill deletes calendar events immediately when a query contains '删除' or '取消' plus an event ID, without any confirmation step, preview, or undo mechanism. In an agent setting, this makes destructive actions easy to trigger accidentally or through ambiguous/paraphrased user input, causing loss of user scheduling data.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The title, description, and usage examples all assume Chinese-language interaction, which may amount to a language-policy issue if the organization expects language choice rather than a forced locale. There is no statement that the skill is Chinese-only, region-specific, or that users may choose another language.
Content: No source excerpt is available for this finding.