Skip to content
skillsafebeta
← Report library
Purpose / Other

Dbs Action Skill Security Audit

What the author says it does (original text)

用阿德勒心理学框架诊断执行阻滞。用户知道该做什么却迟迟不做、反复拖延或行动中断时使用。

Independent security check

Security risks found

Files checked
2
Risks found
2
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.Risks found: 1
Low risk

An optional follow-up command reads sensitive diagnosis content, but its data boundary cannot be verified

Source references: 3
What we found

After the user accepts the diagnosis, the Skill suggests invoking another installed command and explicitly says it will read the current result and the user's goal. Psychological difficulties, financial goals, and self-assessments can be sensitive, while the supplied source does not show how `/dbs` stores, transmits, or deletes them.

Why this matters

If the actual `/dbs` implementation persists context or sends it to an external service, sensitive psychological or financial information could enter storage or services the user did not expect. The available evidence does not establish that such storage or transmission occurs.

What this evidence establishes

The source optionally directs an accepting user toward `/dbs` and explicitly says that command will read the current diagnosis and the user's goal, which could expose sensitive psychological or financial information to another component. However, the invocation is optional and should only be suggested when the command is installed and the user asks about next steps. No `/dbs` implementation, storage location, network behavior, retention period, or deletion process is shown, so disclosure or persistence cannot be established. Before invoking it, users can request those data-boundary details and limit what they provide.

This assessment concerns the code and conditions shown, not proof that harm has occurred.
SKILL.md:216In the instructionsOpen original file
## 留档（可选）执行力诊断里挖出来的「真实目的」尤其值得存——下次再卡住时可以直接对照：> 这次分析完成后，如果你想保存结论或继续推进，输入 `/dbs`。它会读取本轮结果和你的明确目标，判断当前该做什么。只在用户已经接受诊断结论时提，用户还在抗拒的时候不要提。
Show 2 other places
SKILL.md:222In the instructionsOpen original file
只在用户已经接受诊断结论时提，用户还在抗拒的时候不要提。
SKILL.md:234In the instructionsOpen original file
完成当前任务后直接结束。只有用户明确询问下一步，且当前环境已经安装 `/dbs` 时，简短提示：「下一步不确定时，可以输入 `/dbs`。」
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.Risks found: 1
Medium risk

Predetermined psychological conclusions may dismiss real barriers and misdirect decisions

Source references: 4
What we found

The Skill assumes that nearly all entrepreneurial problems are disguised avoidance and inferiority, and instructs the AI to look past the problem the user reports. It even frames workload, lack of funds, or family opposition as forms of self-deception. These are not individualized conclusions based on an adequate assessment.

Why this matters

A user may be wrongly blamed, overlook genuine financial, health, family, workload, or safety constraints, and make unsuitable business, spending, or life decisions under shame or pressure. Users already experiencing psychological distress may be particularly affected.

The live instructions presume that a user's problem is probably avoidance, directly attribute procrastination to inferiority, and tell the AI to look past the problem the user reports. They also frame potentially real constraints—workload, lack of funds, or family opposition—as self-deception. Without screening for health, finances, caregiving, or coercive relationships, this could dismiss genuine barriers and distort decisions. Users can ask the author to screen alternative causes, avoid definitive psychological labels, and recommend professional assessment before consequential decisions.

SKILL.md:12In the instructionsOpen original file
**核心判断：99% 的创业问题是伪装成创业问题的心理问题。** 如果用户来找你，大概率他的问题不是"不知道怎么做"，而是"知道怎么做但在逃避"。
Show 3 other places
SKILL.md:24In the instructionsOpen original file
所以拖延的根源是**自卑**——无法承担执行了却没有结果的风险。
SKILL.md:122In the instructionsOpen original file
**表现**：把不行动归咎于外部。- 「家人不支持我」- 「我现在的工作太忙了」- 「没有启动资金」**诊断**（阿德勒视角）：大多数情况下，你没有被强迫。在对方手里没枪的情况下，他很难真正强迫你。「被强迫」是一种自我欺骗——你是在自愿选择后归咎于外部。**一句话**：你不是被困住了，你是选择了留在原地。
SKILL.md:174In the instructionsOpen original file
1. **像医生一样冷静。** 不评判，不嘲讽，但也不安慰。诊断就是诊断。2. **直指核心。** 不要在表面问题上打转。用户说的"问题"通常不是真正的问题。3. **引用阿德勒但不掉书袋。** 用大白话解释心理机制。
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.No risks found

Inside this skill

6 instruction sections

The Skill first asks the user to describe the blockage, maps the account to one of six predefined signals, and produces a fixed-format report containing a psychological cause, action advice, and a one-line prescription.

View source
SKILL.md:50In the instructionsOpen original file
问用户：**「你现在卡在什么地方？说具体的。」**然后闭嘴听。不要急着诊断。让用户说完。
SKILL.md:58In the instructionsOpen original file
在用户的描述中识别以下信号，每个信号对应一个诊断：
SKILL.md:134In the instructionsOpen original file
### Phase 3：输出诊断报告```# 执行力诊断报告## 你描述的问题{用户说的话}## 我看到的信号- 信号类型：{A/B/C/D/E/F}- 具体表现：{用户的具体行为}## 诊断{根据阿德勒框架的分析}## 真正的问题是什么{一段话，直接指出用户不做的真正原因}

It says it is not psychological counseling and tells users with persistent emotional distress to seek professional help, although this disclaimer appears after the psychological diagnosis.

View source
SKILL.md:165In the instructionsOpen original file
## ⚠️ 免责声明这是一个基于 dontbesilent 推文逻辑的 AI 诊断工具，不是心理咨询。如果你有持续的情绪困扰，请寻求专业心理咨询师的帮助。```
SKILL.md:184In the instructionsOpen original file
- 不要把不执行归因于"信息不够"——信息永远不够，但这不是原因- 不要假装你能替代心理咨询师——标注免责声明

The diagnosis can be handed to a separately installed `/dbs` workflow; the text says that workflow will read the current result and the user's stated goal, but no `/dbs` implementation or data-handling details are supplied.

View source
SKILL.md:216In the instructionsOpen original file
## 留档（可选）执行力诊断里挖出来的「真实目的」尤其值得存——下次再卡住时可以直接对照：> 这次分析完成后，如果你想保存结论或继续推进，输入 `/dbs`。它会读取本轮结果和你的明确目标，判断当前该做什么。
SKILL.md:234In the instructionsOpen original file
完成当前任务后直接结束。只有用户明确询问下一步，且当前环境已经安装 `/dbs` 时，简短提示：「下一步不确定时，可以输入 `/dbs`。」
Start here · InstructionsSKILL.md
dbs-action
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source.
Files and check records2 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included
  • agents/openai.yamlFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions
  • agents/openai.yamlSupporting file
Lines read
240
File checksum (to compare versions)
3fff018b70b6b7491fb2731d9d099ec80448073d8d74ea2f2e0bd087d0c62e7b