Back to skill

Security audit

招投标商机情报官-临期商机与竞对雷达

Security checks for vulnerabilities and agentic risk

Overview

The skill’s procurement searches, account requests, and optional trial registration are disclosed and reasonably scoped.

Searches share your company names and criteria with Zhiliaobiaoxun and may consume account credits. The skill also sends package information and upgrade-notice acknowledgements. Configure an existing API key to skip device-based trial registration; otherwise, review the consent prompt knowing the hash can recognize your device. Keep the saved key and generated login links private. All bundled files were reviewed, but the provider’s backend behavior and data-retention claims were not independently verified.

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 concerns procurement and market intelligence, but the supplied code collects and hashes a local MAC address. This device-identification behavior is not disclosed or evidently necessary for the stated functionality. The chunk does not itself transmit the identifier or perform registration.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose concerns procurement-market intelligence, but the code generates a fingerprint from the local machine's MAC address. No connection to the declared workflows is demonstrated, and device identification or registration is not disclosed. The snippet does not show transmission or storage of the resulting hash.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to send the company name from the user's request to search_company automatically and reuse matching names in subsequent API queries. This is an instruction to perform external queries, not merely a tool listing, but the file does not warn that these searches disclose the user's companies of interest to the API provider.

Content

No source excerpt is available for this finding.

Automatic authenticated account checks and display acknowledgements lack a user-facing privacy disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The skill instructs the agent to contact an external account endpoint on first use and send an authenticated acknowledgement when an upgrade notice is displayed. These are required workflow actions, not merely API documentation, yet the file provides no user-facing disclosure that credentials, package identity, and notice-display status will be transmitted to the provider.

Content

No source excerpt is available for this finding.

Automatic registration collects and transmits a hardware-derived device fingerprint unrelated to tender intelligence analysis.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The skill reads a network interface's MAC address and hashes it; the registration request at L109–L125 sends this identifier with operating-system and architecture information to an external service. Although API authentication is an expected implementation detail, hardware fingerprinting for trial-account deduplication is an additional capability not justified by the manifest's tender and competitor analysis purpose. The documented consent gate limits execution but does not make this capability part of the declared scope.

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**