Back to skill

Security audit

标讯 · 浙江招标中标与招投标数据查询

Security checks for vulnerabilities and agentic risk

Overview

The bidding tools fit their purpose, but conflicting sign-in instructions could trigger new account registration when an existing account key fails.

Review the conflicting credential-recovery rules before unattended use. An existing key should be repaired or replaced under your direction rather than triggering registration. Searches send company names and filters to 知了标讯 and may spend credits. Optional trial registration sends device details after consent and saves a local key; configuring your own key skips it. Keep saved keys and automatic-login links private. This review covers the bundled instructions, not the provider's server-side data handling.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose does not disclose local hardware identification or device fingerprinting. This code performs those operations rather than procurement-related querying or analysis, with no demonstrated connection to the declared functions. It does not itself transmit the identifier, register an account, or access bidding data.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied chunk performs device identification rather than procurement-data retrieval or analysis. Although the file name suggests registration, the chunk provides no demonstrated connection to necessary account authentication or another declared feature. It shows no network transmission or persistent storage, so those behaviors are not inferred.

Content

No source excerpt is available for this finding.

The authentication-error workflow directs automatic registration even when an API key already exists, contradicting the registration prerequisite.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The error table directs registration for invalid, expired, or disabled keys even when credentials already exist, contradicting the explicit registration prerequisite. An agent following that branch could unnecessarily initiate device collection and account creation or replace the intended account context; the separate consent requirement limits, but does not eliminate, this risk.

Content

No source excerpt is available for this finding.

Automatic company searches transmit user-supplied company names to an external API without a privacy disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

This section instructs the agent to send the company name from the user's request to search_company and automatically use matched company names in subsequent queries. Unlike a passive API catalog entry, this is an executable workflow, but it provides no user-facing notice that the user's search terms will be transmitted to the external 知了标讯 service.

Content

No source excerpt is available for this finding.

Automatic registration collects and transmits a persistent hardware fingerprint beyond the tender-query skill's stated purpose.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The registration request sends operating-system information, CPU architecture, and a SHA256 hash of the device's MAC address, collected by the commands at L065–L099. Authentication is expected for the described tender and account-balance queries, but hardware-based device identification for trial-account deduplication is a separate capability not declared in the manifest. The explicit consent requirement limits the risk but does not bring this capability within the stated purpose.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/auto-register.md (reported line 130)May include surrounding context.

md
> ### ⚠️ 请求体必须用 JSON 序列化函数生成,不要手拼字符串
>
> 用 `json.dumps(payload)` / `requests.post(url, json=payload)` / `JSON.stringify(payload)`,
> 或 `curl -d @file`;**不要用字符串拼接,也不要用 Python 的 `str(dict)`**
> (后者产出单引号,服务端会报 `Expecting property name enclosed in double quotes`)。
>

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/auto-register.md (reported line 131)May include surrounding context.

md
> ### ⚠️ 请求体必须用 JSON 序列化函数生成,不要手拼字符串
>
> 用 `json.dumps(payload)` / `requests.post(url, json=payload)` / `JSON.stringify(payload)`,
> 或 `curl -d @file`;**不要用字符串拼接,也不要用 Python 的 `str(dict)`**
> (后者产出单引号,服务端会报 `Expecting property name enclosed in double quotes`)。
>
> 历史教训:曾有版本采集 `home_path`,Windows 的 `C:\Users\alice` 直接拼进 JSON 字符串时

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/auto-register.md (reported line 195)May include surrounding context.

text

注意事项:
- 目录不存在时先 `mkdir -p ~/.zlbx`
- 文件已存在时**合并而非覆盖**(保留用户可能的其他配置)
- `source: "auto"` 字段必须写入,**这是后续判断「是否输出自动登录链接」的关键依据**