Back to skill

Security audit

Dataify Google Hotels

Security checks for vulnerabilities and agentic risk

Overview

The skill does perform the advertised hotel search through Dataify, but its API token handling is review-worthy and could expose or persist credentials unnecessarily.

Install only if you are comfortable sending hotel search details and a Dataify API token to Dataify. Prefer a session-scoped environment variable or a proper secret manager, avoid passing the token with --token, and do not follow the persistent shell startup-file examples unless you accept the credential exposure risk. Rotate the token if it was already stored in shell config files.

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

Plaintext API Token Persistence and Command-Line Credential Exposure

Content
View full analysis

Vulnerability Details

File Location: SKILL.zh-CN.md:21-48; scripts/google_hotels.py:258, 649-656
Vulnerability Type: Plaintext credential storage and unsafe credential input
Risk Level: Medium

Vulnerable Code

SKILL.zh-CN.md:21-48 recommends permanently storing the token in plaintext shell initialization files:

markdown
## 设置 DATAIFY_API_TOKEN

推荐使用永久环境变量,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
text

`scripts/google_hotels.py:258` permits the secret to be supplied on the command line:

```python
parser.add_argument("--token", help="Dataify API token. Bearer prefix is optional.")

scripts/google_hotels.py:649-656 also copies the normalized authorization value back into the process environment:

python
def get_authorization(token_arg: str | None) -> str | None:
    token = clean_value(token_arg) or clean_value(os.environ.get("DATAIFY_API_TOKEN"))
    if not token:
        return None
    if not token.lower().startswith("bearer "):
        token = f"Bearer {token}"
    os.environ["DATAIFY_API_TOKEN"] = token
    return token

Technical Analysis

The localized instructions recommend writing the API token directly into .bashrc, .zshrc, or a persistent user-level Windows environment variable. These locations are plaintext configuration stores that may be read by other processes executing as the same user, included in backups, collected in diagnostics, synchronized between systems, or accidentally ...[truncated 2551 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove the recommendation to place plaintext tokens in .bashrc, .zshrc, or persistent user environment variables by default.
  2. Make the English and localized instructions consistent. Recommend a session-scoped environment variable first:
    • POSIX shells: export DATAIFY_API_TOKEN="..."
    • PowerShell: $env:DATAIFY_API_TOKEN = "..."
    • Command Prompt: set DATAIFY_API_TOKEN=...
  3. For persistent storage, recommend an operating-system credential manager or secret-management service rather than shell initialization files.
  4. Deprecate or remove --token. If compatibility requires retaining it, display a warning that command-line secrets may be exposed through shell history and process listings.
  5. Remove os.environ["DATAIFY_API_TOKEN"] = token. Keep the normalized authorization value only in local memory and pass it directly to call_api.
  6. Continue preventing token values from appearing in dry-run output, logs, errors, result tables, telemetry, and dashboard attribution parameters.
  7. Document token rotation and revocation procedures for users who may already have stored credentials in plaintext.
  8. Add automated tests that verify generated output and error handling never contain the supplied token or the complete Authorization header.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (11)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description says the skill searches Google Hotels for hotel discovery, prices, or availability. However, the supplied code only reads local files (references/api.md and scripts/.py), extracts parameter metadata/defaults, parses command-line arguments, and prints a confirmation table. There is no network access, no Google Hotels interaction, no hotel-specific logic, and no Booking.com handling. This is a materially different primary purpose, so the description does not accurately represent the code.

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
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

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
92% confidence
Finding

The skill directs the agent to read local files, inspect environment state, and run a Python script that will likely make network requests, but it declares no explicit tool scope or permission boundaries. This creates an authorization gap where the runtime may permit broader capabilities than users or platform policy expect, increasing the risk of unintended file, env, or network access.

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 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
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 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.

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.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill reads an API token from DATAIFY_API_TOKEN and then writes the normalized Bearer token back into the process environment. Persisting credentials in environment state is unnecessary for a single hotel-search request and can broaden exposure if other code in the same process later reads, logs, or forwards environment variables.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script transmits user-supplied hotel search parameters and the authorization token to a third-party external service. While this is the intended function of the skill, the execution path does not present a clear runtime warning or consent checkpoint, so users may unknowingly disclose travel plans, occupancy details, and credentials to an external processor.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

Lines L15-L16 specify hl and gl locale parameters and present example language and region codes, while the rest of the document is written in Chinese. This creates a mild natural-language locale policy concern because the skill documentation does not state whether locale should follow the user's preference or why these locales are emphasized.

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_hotels.py (reported line 562)May include surrounding context.

python
params[normalized_key] = cleaned

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