ClawHub
Back to skill

Security audit

QinYu

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public cryptocurrency market data and generates local analysis without account access, persistence, or hidden execution.

Install only if you are comfortable with the skill contacting public crypto data APIs and providing Chinese-language market analysis. Treat its trading and leverage suggestions as informational, not financial advice.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill advertises network-backed cryptocurrency analysis capabilities and references multiple external APIs, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a governance and transparency gap: an agent may invoke network-capable code without a clearly documented least-privilege boundary, making review, sandboxing, and policy enforcement harder.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file introduces the skill title and core description in Chinese, while the manifest description is in English, but there is no explicit user opt-in or stated language-selection behavior. Under the language/locale policy, forcing or defaulting to a specific language without user choice can be a policy violation unless clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This codebase presents its identity, analysis output, and user-facing strings entirely in Chinese, with no option for users to choose another language or locale. The policy scope covers natural-language constraints in code files, and this implementation effectively imposes a specific language by default rather than offering a choice.

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 · scripts/qinyu.py (reported line 17)May include surrounding context.

python
def fetch_binance_price(self, symbol: str) -> Optional[Dict]:
        try:
            url = f"https://api.binance.com/api/v3/ticker/24hr?symbol={symbol}"
            with urllib.request.urlopen(url, timeout=10) as response:
                return json.loads(response.read())
        except:

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/qinyu.py (reported line 25)May include surrounding context.

python
def fetch_binance_price(self, symbol: str) -> Optional[Dict]:
        try:
            url = f"https://api.binance.com/api/v3/ticker/24hr?symbol={symbol}"
            with urllib.request.urlopen(url, timeout=10) as response:
                return json.loads(response.read())
        except:

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/qinyu.py (reported line 33)May include surrounding context.

python
def fetch_coingecko_global(self) -> Optional[Dict]:
        try:
            url = "https://api.coingecko.com/api/v3/global"
            with urllib.request.urlopen(url, timeout=10) as response:
                return json.loads(response.read())
        except:

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/qinyu.py (reported line 41)May include surrounding context.

python
def fetch_coingecko_global(self) -> Optional[Dict]:
        try:
            url = "https://api.coingecko.com/api/v3/global"
            with urllib.request.urlopen(url, timeout=10) as response:
                return json.loads(response.read())
        except:

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/qinyu.py (reported line 50)May include surrounding context.

python
def fetch_fear_greed(self) -> Optional[Dict]:
        try:
            url = "https://api.alternative.me/fng/?limit=2"
            with urllib.request.urlopen(url, timeout=10) as response:
                data = json.loads(response.read())
                if data and 'data' in data and len(data['data']) > 0:

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/qinyu.py (reported line 69)May include surrounding context.

python
def fetch_defi_tvl(self) -> Optional[List]:
        try:
            url = "https://api.llama.fi/protocols"
            with urllib.request.urlopen(url, timeout=10) as response:
                return json.loads(response.read())
        except:

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/qinyu.py (reported line 87)May include surrounding context.

python
def fetch_gas_prices(self) -> Optional[Dict]:
        try:
            url = "https://api.etherscan.io/api?module=gastracker&action=gasoracle"
            with urllib.request.urlopen(url, timeout=10) as response:
                data = json.loads(response.read())
                if data.get('status') == '1':

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructional content in Chinese, including headings and usage guidance, but does not indicate that the skill is Chinese-only or offer an alternative language option. Under the natural-language policy rule, forcing a specific language without user opt-in can be a locale policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.