Back to skill

Security audit

汉语词语查询 - 即刻数据

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese dictionary API helper, but it has an under-disclosed endpoint override that can send the API key and user queries to a non-Jike server if the environment is altered.

Review before installing. Use it only with a dedicated low-privilege Jike AppKey, avoid passing the key on the command line, and do not set JIKE_API_BASE_URL unless you fully trust and intend that endpoint. Prefer running it in an environment where outbound access is limited to the official Jike API host.

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/word_query.py:25
Finding

Configurable API endpoint permits AppKey exfiltration

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/word_query.py:244
Finding

AppKey is exposed through command-line arguments and request URLs

Content
View full analysis
`. 2. A proxy, gateway, server, monitoring agent, or diagnostic facility records the full URL. 3. An individual with access to those logs retrieves the AppKey. 4. The individual reuses t ...[truncated 554 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
Findings (6)

Tainted flow: 'url' from os.environ.get (line 244, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

The request target is derived from the JIKE_API_BASE_URL environment variable and then fetched with urlopen without any allowlist or validation. In an agent/runtime context, a user or integrator who can influence environment variables could redirect requests to an arbitrary host, causing SSRF-like outbound requests and leaking the AppKey in the query string to an attacker-controlled endpoint.

Content

Scanner excerpt · scripts/word_query.py (reported line 246)May include surrounding context.

python
"""
    url = f"{API_BASE_URL}{API_PATH_MAP[command]}?{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": ""}

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/word_query.py (reported line 54)May include surrounding context.

python
env_value = os.environ.get(env_name, "").strip()
        if env_value:
            return env_value
    env_file = Path(__file__).parent / ".env"
    if not env_file.exists():
        return ""
    for line in env_file.read_text(encoding="utf-8").splitlines():

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill declares executable requirements and clearly relies on environment variables and network access, but it does not declare an explicit tool scope such as permissions or allowed-tools. That creates a policy gap where an agent may invoke code, read environment secrets, and make outbound requests without a tightly constrained contract, increasing the risk of overbroad execution or secret exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description contains broad natural-language trigger examples like generic requests for meanings, synonyms, and antonyms without clear invocation boundaries. In agent environments, this can cause over-eager routing or accidental activation in loosely related conversations, which may lead to unnecessary external API calls and exposure of user queries to a third-party service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · _meta.json (reported line 8)May include surrounding context.

json
"title": "汉语词语查询 - 即刻数据",
  "description": "支持搜索词语、词语详情、随机词语、近义词查询和反义词查询,返回拼音、解释、出处、用法、近义词和反义词。",
  "env": "JIKE_WORD_QUERY_KEY",
  "api_url": "https://api.jikeapi.cn/v1/word/query",
  "homepage": "https://www.jikeapi.cn/"
}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and all user-facing descriptions specify and assume Chinese-only interaction, and the script’s CLI help and output strings are also written in Chinese. This creates a language/locale constraint without any user-selectable language option or explicit opt-in, which matches the policy-violation category for forced language.

Content

No source excerpt is available for this finding.