ClawHub
Back to skill

Security audit

老黄历查询 - 即刻数据

Security checks across malware telemetry and agentic risk

Overview

This appears to be a focused calendar/lunar-date lookup skill that calls an external API with a configured app key, with some transparency and hardening gaps but no evidence of hidden or destructive behavior.

Install only if you are comfortable sending queried date and time values to the external calendar API. Set the app key through a trusted environment, avoid overriding the API base URL unless you control the endpoint, and treat the app key as a secret that may appear in request URLs or logs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

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

Critical
Category
Data Flow
Content
params = {"date": date_value, "time": time_value, "appkey": appkey}
    url = f"{API_BASE_URL}{API_PATH}?{urllib.parse.urlencode(params)}"
    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
96% confidence
Finding
with urllib.request.urlopen(url, timeout=15) as response:

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger examples include broad natural-language phrases like '今天宜忌是什么' and '某天适合结婚搬家吗', which can overlap with ordinary conversation and increase the chance of accidental invocation. In agent environments, over-broad activation can cause unintended external API calls and disclosure of user-supplied date/time context without a deliberate request to use this specific skill.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description says data is provided by jikeapi.cn, but it does not clearly disclose that user-provided date/time will be transmitted to an external service and authenticated with an app key. This weak transparency can mislead users and downstream agents about data flow, preventing informed consent and making inadvertent third-party sharing more likely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.