Security audit

Crypto Analyst

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly coherent crypto-analysis tool, but it needs review because normal analysis can run unaudited scripts from hard-coded external paths and it handles OKX account credentials with limited safeguards.

Review before installing. Do not run the default OKX analysis unless you are comfortable with its hard-coded external news-script calls, or use --no-news. If you configure OKX keys, use read-only keys with the minimum account permissions, avoid withdrawal/trading permissions, and keep them in a dedicated environment. Install dependencies in an isolated virtual environment and prefer pinned requirements.

A.I.G

Vulnerability Patterns

Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T07 · Tool Hijacking and Spoofing

Error

Location: scripts/okx_analyst.py:829
Finding: Default Execution of Unaudited Scripts Outside the Skill Package
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:140
Finding: Unpinned and Unnecessary Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (37)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 93% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The documented behavior materially exceeds the declared market-analysis purpose by including authenticated balance access via OKX API credentials. That mismatch can mislead users into supplying secrets or approving actions they would not expect from a nominally analytical skill.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The docstring is materially misleading: the script does not use a public endpoint, it performs an authenticated request to a private account-balance API using API credentials from a local .env file. In a security review context, this kind of misrepresentation can cause operators to grant sensitive keys or run the tool under false assumptions, increasing the chance of credential exposure or unauthorized access to private financial data.
Content: No source excerpt is available for this finding.

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/balance_check.py (reported line 17)May include surrounding context.
python
from datetime import datetime def load_env(): """Load OKX credentials from .env""" env_path = os.path.join(os.path.dirname(__file__), '.env') if os.path.exists(env_path): with open(env_path) as f:

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/balance_check.py (reported line 18)May include surrounding context.
python
def load_env(): """Load OKX credentials from .env""" env_path = os.path.join(os.path.dirname(__file__), '.env') if os.path.exists(env_path): with open(env_path) as f: for line in f:

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/balance_check.py (reported line 60)May include surrounding context.
python
import os from dotenv import load_dotenv # 加载环境变量（从 .env 文件） load_dotenv() # OKX API 配置（从环境变量读取，不要硬编码！）

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/okx_analyst.py (reported line 20)May include surrounding context.
python
import os from dotenv import load_dotenv # 加载环境变量（从 .env 文件） load_dotenv() # OKX API 配置（从环境变量读取，不要硬编码！）

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/okx_analyst.py (reported line 36)May include surrounding context.
python
import os from dotenv import load_dotenv # 加载环境变量（从 .env 文件） load_dotenv() # OKX API 配置（从环境变量读取，不要硬编码！）

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill advertises and invokes capabilities that imply shell execution, network access, file reads, and environment-variable use, but it declares no explicit tool scope or permission boundaries. In a skill that references API keys and command execution, missing scope declarations increases the chance of over-broad access and unintended execution paths.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The markdown instructs users to configure OKX API credentials and references balance retrieval, but it does not prominently warn about sensitive credential handling, account-data exposure, or the risks of using live exchange keys. This can lead users to supply powerful secrets to a skill presented mainly as an analysis tool, increasing the chance of credential leakage or misuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger guidance includes broad natural-language phrases like '帮我看看行情', which can cause the skill to activate in routine conversation without clear user intent. In a skill capable of shell/network operations and potentially touching authenticated exchange data, over-broad activation increases the risk of unintended execution and data exposure.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This Python file contains multiple user-facing strings in Chinese, including error messages and account output labels. The policy forbids forcing a specific language without user opt-in, and nothing in the file indicates that the skill is intentionally region-specific or provides a language selection.
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/cross_exchange.py (reported line 35)May include surrounding context.
python
symbol = symbol.upper().replace('-', '') + 'USD' # Try Binance US first, then OKX as fallback reference for base_url in [ f"https://api.binance.us/api/v3/ticker/price?symbol={symbol}", ]: try: r = requests.get(base_url, timeout=10)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This code hardcodes Chinese-language descriptions and output strings in the argument parser and printed results, which imposes a specific language on all users. The file does not provide a language option, fallback, or justification that the skill is intended only for a Chinese-speaking or region-specific audience.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The top-level docstring describes the script as fetching the current Fear & Greed index from alternative.me. In practice, the program also interprets the value and prints actionable market advice, which contradicts the documented intent rather than merely omitting an implementation detail.
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/fear_greed.py (reported line 13)May include surrounding context.
python
import json def get_fear_greed(): url = "https://api.alternative.me/fng/" try: r = requests.get(url, timeout=10) data = r.json()

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The user-facing strings throughout the script are fixed in Chinese, and the skill does not provide any opt-in, locale selection, or justification for enforcing that language. This can violate language/locale policy when users are not given a choice.
Content: No source excerpt is available for this finding.