Temporal Time Manager

• Outcome: Review
• Latest audit: Sep 11, 2026 · 1:06 AM UTC
• Version: 1.0.2

Overview

This is a coherent time-management skill, but it can permanently change or delete synced user data without documented confirmation or recovery safeguards.

Install only if you are comfortable giving this skill API-token access to your aitimemg.cn task data. Before using it, require your agent to confirm exact task or schedule IDs and names before updates or deletions, and be especially cautious because task deletion is described as a hard delete with no documented undo.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The delete operation is tied to vague language like 'delete this task', but the specification does not require a confirmation step, identity verification of which task 'this' refers to, or any recovery path. Because deletion is destructive and the endpoint performs a hard delete, ambiguous conversational references can lead to irreversible loss of user data from a normal dialogue mistake.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The API description explicitly states the task deletion is a hard delete, but it does not warn about irreversible data loss or instruct the agent to alert the user before executing it. In an LLM-driven skill, omission of such guardrails materially increases the chance of permanent deletion from misinterpretation, prompt injection in surrounding conversation, or accidental user phrasing.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill exposes destructive operations such as `delete_task` and `delete_schedule` but does not document any requirement for explicit user confirmation, preview, or undo behavior before deletion. In an agent-driven context, ambiguous natural-language instructions or hallucinated tool calls could cause unintended permanent data loss, especially because this skill directly modifies a user's synced task data on a remote service.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The natural-language descriptions and operational guidance throughout the file are presented only in Chinese, which effectively forces a language choice without user opt-in. The file does not state that the skill is region-specific or provide an alternative language option.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The description says that when a user says roughly 'help me add a task', the agent should call the create_task API. That trigger guidance is broad and may cause the agent to transform casual discussion, brainstorming, or requests for advice into state-changing writes without clearly confirming user intent. In a time-management skill, this creates a real risk of unintended task creation and silent data pollution.

Natural-Language Policy Violations

Low

• Confidence: 77% confidence
• Finding: The description specifies the skill in Chinese and all usage examples and instructions assume Chinese-language interaction, but there is no indication that language choice is optional or that the locale restriction is intentional and justified. This can conflict with language/locale policy expectations when no user opt-in is provided.

Static analysis

No suspicious patterns detected.