ClawHub
Back to skill

Security audit

生日密码 - 即刻数据

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward birthday-query API skill, but users should understand that birthday input and an API key are sent to a third-party service.

Install only if you are comfortable sending the birthday value you provide, plus the configured API key, to api.jikeapi.cn. Use a dedicated low-privilege API key, avoid setting a custom API base URL unless you control it, and invoke the skill only for explicit birthday-password lookups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tainted flow: 'url' from os.environ.get (line 139, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
"""
    url = f"{API_BASE_URL}{API_PATH}?{urllib.parse.urlencode({**params, 'appkey': appkey})}"
    try:
        with urllib.request.urlopen(url, timeout=15) as response:
            return json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        return {"code": exc.code, "message": f"接口请求失败: HTTP {exc.code}", "data": ""}
Confidence
84% confidence
Finding
with urllib.request.urlopen(url, timeout=15) as response:

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill declares required binaries and environment variables and clearly instructs the agent to execute a Python script and call an external API, but the markdown does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users or hosting platforms may not realize the skill can read secrets from environment variables, access local files, and transmit data over the network.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description says the skill applies to broad categories like traditional culture, life knowledge, or matching information, which can cause over-triggering on ordinary conversations. Over-broad activation increases the chance that user-provided data is unnecessarily routed to this third-party-backed skill without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends a birthday value to a third-party API, but the markdown does not clearly warn that user-provided birthday data leaves the local system. Even though a birthday is not always highly sensitive, it is personal data and can become more sensitive when linked with other profile information or conversation context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script places both the birthday query and the AppKey into the URL query string. Query strings are commonly exposed in logs, browser/history-like tooling, proxies, process monitoring, and upstream infrastructure, so secrets and user input may be recorded more broadly than intended. In this skill, the birthday itself is low-sensitivity, but the AppKey is a credential, making URL-based transmission a real security concern.

External Transmission

Medium
Category
Data Exfiltration
Content
直接调用 API：

```text
GET https://api.jikeapi.cn/v1/birthday/pwd?birthday=01-06&appkey=YOUR_APPKEY
```

## AI 使用步骤
Confidence
90% confidence
Finding
https://api.jikeapi.cn/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.