ClawHub
Back to skill

Security audit

彩票助手

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it says, but its Excel export can place unvalidated external lottery data into spreadsheets, which users should review before installing.

Install only if you are comfortable with the skill contacting data.17500.cn and writing export files. Avoid opening generated XLSX files from untrusted or unexpected data without spreadsheet protections, and prefer txt/md/sqlite export if you do not need Excel output.

A.I.G

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
scripts/export.py:259
Finding

Untrusted External Data Can Be Exported as Executable Spreadsheet Formulas

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (20)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code is clearly related to lottery draw querying, so it partially matches the declared domain and supported lottery types. However, the declared description promises substantially more functionality than this code actually provides. The code only downloads plain-text historical draw data from 17500.cn, parses fields for several lottery formats, and exposes a command-line interface for fetching the latest N periods. There is no logic for querying a specific issue number, filtering by date range, exporting to any file formats, or generating recommended numbers based on historical analysis. Because these omitted features are central parts of the declared purpose rather than minor implementation details, the description does not accurately represent what this code chunk actually does.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill instructs the agent to perform network access and write files, but it does not declare any tool scope or permission boundaries. This creates an over-privileged or ambiguously privileged execution model where the host may allow broader capabilities than users expect, increasing the risk of unintended external requests or file writes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger words include very broad everyday terms such as '彩票' and '开奖', making accidental invocation more likely. In a skill that can access the network and write export files, unintended activation can cause unnecessary external requests, surprising outputs, or execution in conversations where the user did not intend to use this skill.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · SKILL.md (reported line 134)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 5)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 11)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 12)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 13)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 14)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 15)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 16)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 17)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 18)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 67)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/apis.md (reported line 75)May include surrounding context.

md
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/query.py (reported line 28)May include surrounding context.

python
def fetch_raw(code, direction="desc", max_chars=None, n=None):
    url_code = _API_TO_URL.get(code, code)
    url = f"https://data.17500.cn/{url_code}_{direction}.txt"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
        "Accept": "text/plain, */*",

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file’s user-facing descriptions and formatting are written in Chinese, indicating the skill is designed to operate in a fixed locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file presents all instructions, labels, and examples only in Chinese, which can amount to a language/locale policy issue when no user opt-in or documented regional limitation is provided. The stated policy asks to flag cases where a skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for its documentation and CLI examples. Under the stated policy, language-specific behavior should not be imposed without offering the user a choice or clearly documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The argument parser description, help text, and examples are all presented only in Chinese, and the script also prints status/error messages in Chinese. This enforces a single language for user interaction without opt-in or alternative locale support.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.