Security audit

Todo Momentum - 3 分钟启动器

Security checks for vulnerabilities and agentic risk

Overview

This is a plain productivity coaching skill that gives small next steps for stuck tasks and does not request code execution, credentials, persistence, or hidden data access.

Installers should expect a Chinese-first productivity helper. It appears safe from a security standpoint, but users who work in English should explicitly ask it to mirror their language if the default Chinese templates are not desired.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The template is written entirely in Chinese and presents fixed output phrasing, which can cause the assistant to respond in a language the user did not request. This is not a code-execution or data-exfiltration issue, but it can degrade usability, violate user expectations, and interfere with accessibility or policy requirements around honoring user language preference.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The recovery script similarly hard-codes Chinese output without user opt-in, which may force an unwanted language switch at a sensitive moment when the user is seeking support. The risk remains low, but the skill context makes consistency with the user's language especially important for clarity and trust.

Static analysis

No suspicious patterns detected.