ClawHub
Back to skill

Security audit

Todo Momentum - 3 分钟启动器

Security checks for vulnerabilities and agentic risk

Overview

This is a plain productivity skill that helps break stuck tasks into small next actions and does not request code execution, credentials, persistence, or broad local access.

Installers should understand this is a Chinese-first productivity helper for breaking tasks into immediate next actions. It is low security risk based on the inspected artifacts, but publishers could improve clarity by documenting language behavior and tighter activation boundaries.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
## Operating Stance

Turn intention into motion. Do not moralize, scold, or optimize too early. Treat procrastination as a design signal: the task is probably too vague, too large, too emotionally loaded, missing a prompt, or missing feedback.

Default to Chinese when the user writes in Chinese.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
- `SKILL.md` is the source of truth for Codex, OpenClaw, Hermes, and ClawHub-style loaders.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The template is written entirely in Chinese and presents the expected response format in that language, without offering a user choice or documenting a locale-specific constraint. This can violate language/locale policy when applied to users who did not opt into Chinese output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and core skill description are presented in Chinese, while the file does not state that the skill is region-specific or allow the user to choose their preferred language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

As a manifest file, this should be checked for vague triggers. The default prompt describes invocation in natural language ('turn my stuck todo...') but does not define any explicit trigger scope, exclusions, or negative examples, which could overlap with common productivity requests and make activation boundaries unclear.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation guidance says to use this reference when the user asks to 'start a task,' 'recover after falling off,' or 'reduce resistance,' which are broad, everyday phrases without clear boundaries. The file does not provide explicit trigger phrases, exclusions, or negative examples to distinguish when this skill should activate versus when more general productivity advice is intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The recovery script directs assistant output in Chinese only, with no indication that the user can choose another language. Because this file is a reusable reference, the lack of opt-in or justification for a fixed language is a policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This manifest file describes a wide range of situations such as procrastinated tasks, stuck tasks, vague goals, projects, chores, and habits, but it does not provide any explicit trigger phrases, scope boundaries, or exclusion conditions. Because the activation context is broad and underspecified, the skill could be invoked for many ordinary planning or productivity requests unintentionally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The display name and description are written entirely in Chinese, which may indicate a language-specific skill experience, but the manifest does not state that this is optional, user-selected, or limited to a Chinese-speaking audience. Under the policy, locale or language constraints should be explicit, optional, or justified when imposed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.