Back to skill

Security audit

BSC Analytics BSC生态分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly BSC analytics content, but it ships payment-verification code with an exposed API key and can send wallet addresses to an external service without clear user-facing disclosure.

Review this before installing. Treat the hardcoded SkillPay key as exposed and require the publisher to rotate it and remove it from the package. Do not provide a wallet address unless you are comfortable sending it to the SkillPay service for verification. Also treat the analytics as static examples or heuristics unless the publisher adds live data sources, provenance, and clearer financial-advice limits.

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
payment.py:15
Finding

Hard-Coded Payment API Credential in Distributed Source and Metadata

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
payment.py:31
Finding

Undisclosed Transmission of User Wallet Addresses to an External Payment Service

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (19)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明的功能聚焦于 BSC/BNB Chain 分析与情报能力,但提供的代码没有任何链上分析、DeFi 协议评估、数据监控、项目分析或投资机会发现逻辑。其主要目的完全是商业化访问控制:验证支付、提示付款、返回支付信息。虽然“付费验证”可能是某个 Skill 的配套基础设施,但从这段代码本身看,其行为与声明的核心能力明显不一致,且包含未声明的外部支付 API 访问与访问门控能力。因此应判定为描述与实际行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

声明描述的是“综合分析工具”,覆盖监控、发现、情报、DeFi 分析等多项能力;但提供的代码只包含一个 BSCProjectEvaluator 类,对传入的项目元数据做启发式打分,并输出评估报告。代码没有网络请求、链上交互、数据抓取、监控调度、告警机制或机会发现逻辑,因此与声明的主要能力范围存在实质性不符。虽然“项目评估”和部分“风险评估”与声明部分重合,但整体描述明显夸大了实际代码能力。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是广泛的 BSC 生态分析与监控能力,属于综合研究/情报类工具;但代码只提供单一的收益估算功能,针对少量预设 DeFi 农场按固定 APY 和简单费用模型进行计算与排名。它没有访问链上数据、没有监控逻辑、没有项目基本面评估、没有情报采集,也没有真正的预警机制。因此其实际主要用途明显比声明狭窄且不同,构成描述与行为不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Skill 触发范围写得非常宽泛,覆盖‘分析 BSC 生态、评估项目、发现投资机会、获取情报’等大量常见投资分析请求,容易在缺乏明确边界时被过度激活。对金融/投资场景而言,过宽触发会放大误导性输出、在错误上下文中提供高风险建议,尤其当内容还包含收益机会、套利、空投等诱导性主题时更值得警惕。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

Natural-language content across the description and documentation is presented entirely in Chinese, with no indication that users may choose another language. This can violate language/locale policy when a skill implicitly forces one language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description is entirely in Chinese, which imposes a specific language on users without any opt-in or indication that the skill is intentionally region-specific. Under the policy, language constraints should either offer user choice or be clearly justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file introduces payment-gating and monetization logic that is not part of the stated BSC analytics functionality. Hidden or undocumented monetization changes the skill’s behavior, can surprise operators and users, and may be used to restrict access or exfiltrate payment-related data outside the expected trust boundary.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The file contains an external transmission endpoint and pairs it with a hardcoded live API key, causing skill execution to send payment-verification data to a third-party service. In context, this is more dangerous because the skill is presented as analytics tooling, yet it quietly introduces outbound payment-related communication and embeds a reusable secret directly in source code.

Content

Scanner excerpt · payment.py (reported line 15)May include surrounding context.

python
from datetime import datetime

# SkillPay API 配置
SKILLPAY_API_URL = "https://api.skillpay.io/v1"
SKILLPAY_API_KEY = "sk_f03aa8f8bbcf79f7aa11c112d904780f22e62add1464e3c41a79600a451eb1d2"
SKILL_SLUG = "shenmeng-bsc-analytics"
PRICE = "0.01"  # USDT

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The code adds payment verification capability unrelated to the declared analytics purpose, expanding the skill’s privileges and network interactions without an obvious functional need. This creates unnecessary attack surface and trust risk, especially because the module can block skill use and communicate with an external payment service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The verification request transmits the user's wallet address and timestamp to an external API without any point-of-use disclosure or consent flow. Wallet addresses are sensitive identifiers in blockchain contexts because they enable linkage of a user’s on-chain activity, and silent sharing with a third party can violate privacy expectations and policy requirements.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file is described and branded as a BSC ecosystem monitor, but the implementation uses only hardcoded sample protocol values and timestamps them as if they were current monitoring output. In an analytics/investment context, this can mislead users into making decisions based on fabricated or stale data while believing it reflects live on-chain conditions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains user-facing natural-language content that effectively forces a specific language/locale, including the module description and later report text, with no opt-in or alternative. The policy explicitly calls for flagging language or locale constraints unless the skill offers user choice or clearly documents a justified regional requirement.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill generates investment recommendations, risk levels, and yield opportunities from simplistic heuristics based only on hardcoded TVL/APY thresholds. In a financial analysis skill, presenting these outputs as substantive analytics can cause users to overtrust low-quality advice and underestimate risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill prints analysis reports, labels, and investment recommendations entirely in Chinese, which is a natural-language policy issue under the locale/language rule. There is no evidence of a user-selectable language setting or documentation justifying a Chinese-only output requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains user-facing descriptions, docstrings, and report text in Chinese, beginning with the module header and continuing throughout the generated report. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module description and all user-facing strings are written exclusively in Chinese, and the script provides no option for users to select another language. This creates a locale-policy issue because the skill implicitly enforces a specific language without opt-in or justification that it is region-specific only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The module docstring and user-facing output strings are written in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking audience. This can violate language or locale policy when a skill implicitly forces one language by default.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest frames the skill as an analysis and monitoring tool, which naturally covers computing and presenting analytics, but does not mention persisting results. The main function saves a JSON report under /tmp, adding a local write side effect beyond the stated descriptive scope.

Content

No source excerpt is available for this finding.