Back to skill

Security audit

Dataify Google AI Mode

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real Dataify Google AI Mode search helper, but it needs review because one localized guide recommends permanently storing API tokens in plaintext shell settings.

Review the token setup instructions before installing. Use a session-scoped DATAIFY_API_TOKEN or a proper secret manager instead of appending the token to shell startup files; rotate the token if it has already been stored in dotfiles or synced backups.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.zh-CN.md:21
Finding

Persistent plaintext storage of the Dataify API token

Content
View full analysis

Vulnerability Details

File Location: SKILL.zh-CN.md, lines 21–48; vulnerable commands at lines 28, 40, and 47
Vulnerability Type: Plaintext credential persistence
Risk Level: Medium

Vulnerable Code

powershell
[Environment]::SetEnvironmentVariable("DATAIFY_API_TOKEN", "your_token_here", "User")
bash
echo 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.bashrc
source ~/.bashrc
bash
echo 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.zshrc
source ~/.zshrc

Technical Analysis

The localized instructions recommend permanently storing DATAIFY_API_TOKEN as a user environment variable or directly in plaintext shell initialization files. Persistent storage is not required for the Skill's declared search functionality because the token can be supplied through a session-scoped environment variable.

On Linux and macOS, the token becomes readable plaintext in .bashrc or .zshrc. Any process or local user with permission to read these files can recover it. The secret may also be retained in workstation backups, configuration synchronization systems, diagnostic archives, or accidentally shared dotfile repositories.

On Windows, the user-scoped environment variable is persistent and may be retrievable by processes running in the same user context. It is not protected like a secret stored in an operating-system credential vault.

These instructions also conflict with the session-scoped-first account policy later in the same document and in SKILL.md, which requires showing a session-scoped setup command first. The behavior is best classified as an insecure credential-handling practice rather than system persistence because it does not install a service, scheduled task, startup backdoor, or executable hook.

Attack Path

  1. A user follows the localized setup instructions and replaces your_token_here with a valid Dataify API token.
  2. The token is written to a persist ...[truncated 1152 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove the recommendation to append API tokens to .bashrc or .zshrc.
  2. Remove persistent user-environment-variable setup as the default Windows recommendation.
  3. Present only session-scoped commands by default:
    • macOS/Linux: export DATAIFY_API_TOKEN="..."
    • PowerShell: $env:DATAIFY_API_TOKEN = "..."
    • Command Prompt: set DATAIFY_API_TOKEN=...
  4. For persistent storage, recommend an operating-system credential manager or dedicated secret-management facility rather than plaintext configuration files.
  5. If a user explicitly requests shell-profile storage, warn that the token will be stored in plaintext and advise restrictive file permissions, exclusion from version control and synchronization, and regular token rotation.
  6. Align SKILL.zh-CN.md with the account policy in SKILL.md: never ask users to paste tokens into chat, never print token values, and verify only whether the environment variable is present.
  7. Advise users who already followed these instructions to remove the token from shell profiles, inspect backups and dotfile repositories for copies, and rotate the exposed token.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (14)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description claims a runtime search skill for Google AI Mode. The actual code only reads local files under references/ and scripts/, parses parameter metadata, accepts CLI arguments/JSON, and prints a confirmation table. There is no network access, no Google API invocation, no AI Mode selection logic based on user intent, and no search-result handling. This is a materially different primary purpose, so the description does not accurately represent the code chunk.

Content

No source excerpt is available for this finding.

YARA rule 'backdoor_persistence': Backdoor persistence with malicious payloads (shell commands, SSH key injection, hidden root users) [malware]

High
Category
YARA Match
Confidence
87% confidence
Finding

The skill recommends persisting an API token by appending it directly into shell startup files such as ~/.bashrc or ~/.zshrc. While not malware, this creates long-lived plaintext credential storage in common dotfiles that may be exposed through backups, logs, accidental sharing, local compromise, or later prompt/tool access, making credential theft easier in the agent context.

Content

Scanner excerpt · SKILL.zh-CN.md (reported line 40)May include surrounding context.

量,而不是只在当前终端临时设置。

Windows PowerShell,当前用户永久设置:

powershell
[Environment]::SetEnvironmentVariable("DATAIFY_API_TOKEN", "your_token_here", "User")

然后重新打开 PowerShell。如果当前会话也要立即生效,再执行:

powershell
$env:DATAIFY_API_TOKEN = "your_token_here"

macOS 或 Linux,bash 永久设置:

bash
echo 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.bashrc
source ~/.bashrc

macOS 或 Linux,zsh 永久设置:

bash
echo 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.zshrc
source ~/.zshrc

参考文件

  • references/ 目录下的 API 文档包含完整的字段列表和说明。
  • 当字段行为、允许的值或响应格式不明确时,请查阅参考文档。

注意事项

  • 始终使用 Content-Type: application/x-www-form-urlencoded 提交 API 请求。
  • 保持请求值为字符串类型。
  • 省略用户未请求的可选字段。

结果呈现

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill directs the agent to read local files, inspect environment state, and make a networked API call, but it does not declare any explicit tool scope or allowed-tools boundary. That mismatch increases the chance of over-broad execution in hosts that rely on manifest-declared permissions, enabling unintended access to environment variables or local files during a search workflow.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
## Account CTA policy

- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.
- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.
- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.
- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.
- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.zh-CN.md (reported line 80)May include surrounding context.

md
## Account CTA policy

- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.
- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.
- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.
- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.
- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.
- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.
- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.
- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.
- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.
- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.
- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.zh-CN.md (reported line 82)May include surrounding context.

md
- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.
- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.
- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.
- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.
- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.
- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.
- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L03 将触发条件描述为“当用户使用 Google AI Model 搜索信息时”,范围非常宽,没有说明具体触发短语、上下文边界或排除条件。对于 markdown 文件,这类宽泛描述容易覆盖普通日常搜索请求,增加技能被非预期调用的风险。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown mixes English headings with Chinese-only field descriptions such as '固定使用', '用户要查询的问题或关键词', and other parameter explanations. That creates a language-policy issue because the file imposes a specific language for key usage guidance without user opt-in or any stated justification that the document is intended only for a Chinese-speaking audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

L06 标题明确标注为“中文版”,但文档中未说明这是用户主动选择的语言版本,也未提供语言切换或选择机制。按自然语言策略,若技能默认强制特定语言而没有用户选择或明确的区域性理由,可能构成语言/区域策略问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The token-missing message is hard-coded entirely in Chinese, which imposes a specific language on users regardless of their locale or preferences. The file does not provide any opt-in, fallback, or documented justification for this language constraint.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/google_ai_mode.py (reported line 245)May include surrounding context.

python
params[key] = cleaned

    for field in FIELDS:
        value = clean_value(getattr(args, field))
        if value is not None:
            params[field] = value

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code emits CLI error messages only in Chinese (不是有效 JSON, 必须是 JSON object), which is a natural-language locale choice embedded in a code file. The file does not offer any user opt-in, fallback language, or documentation indicating the skill is intentionally restricted to Chinese users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The termination message 未找到 references/*api.md is user-visible natural language that enforces a specific locale. Under the policy, forcing a language without user choice or clear documented justification is a reportable issue.

Content

No source excerpt is available for this finding.