专利地域分布

• Outcome: Review
• Latest audit: Oct 20, 2026 · 11:01 AM UTC
• Version: 1.0.2

Overview

The patent-analysis workflow is legitimate, but weaknesses in credential protection and file-cache containment warrant review before installation.

Request fixes for credential routing and cache containment before supplying a paid API key. Keep keys out of chat and shared plaintext files, use a restricted key with a spending limit, and send only research details you authorize PatentMax to receive. Cross-check unexpectedly empty regional statistics.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• Taint Tracking: Direct Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (35)

Tainted flow: 'req' from os.environ.get (line 138, credential/environment) → urllib.request.urlopen (network output)

Critical

• Category: Data Flow
• Confidence: 90% confidence

Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/patentmax_client.py (reported line 142)May include surrounding context.

python

req.add_header("Content-Type", "application/json")
    req.add_header("Accept", "application/json")
    try:
        with urllib.request.urlopen(req, timeout=30) as response:
            payload = json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        message = _server_message(exc.read().decode("utf-8", "replace"))

Tainted flow: 'req' from os.environ.get (line 333, credential/environment) → urllib.request.urlopen (network output)

Critical

• Category: Data Flow
• Confidence: 96% confidence

Finding

Sending the API key to the intended patent service is necessary, but the authenticated request accepts an unrestricted base URL, including HTTP, and uses urllib's default redirect handling, which can retain the Authorization header across origins. A misconfigured endpoint or a redirect to an attacker-controlled host could therefore disclose the bearer key and enable unauthorized paid requests.

Content

Scanner excerpt · scripts/patentmax_client.py (reported line 344)May include surrounding context.

python

req.add_header(key, value)

    try:
        with urllib.request.urlopen(req, timeout=TIMEOUT) as response:
            payload = response.read()
            # 服务端每个响应都回本次实扣和扣完后的余额。记下来，供 _spent/_balance 输出。
            # 拿服务端的真值，而不是在本地累加估价：跨进程累加迟早算岔，

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The supplied command does not analyze patents or generate regional tables. Although using an API key could support patent analysis, printing part of the credential is an undeclared disclosure behavior, not a necessary implementation detail of the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The code partially supports the declared purpose: its stats command accepts province, city, countryCode, and applicant dimensions, which could be combined to analyze regional distributions and leading organizations. However, it also exposes substantial independently callable patent-research capabilities outside that purpose. The supplied chunk does not assemble a regional table with leading organizations or export that table; its CSV export contains individual candidate patents. Authentication, API requests, billing controls, and caching are supporting implementation details and are not independently treated as mismatches. The finding concerns the supplied code's broader functional scope, not evidence of malicious behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The supplied commands perform individual-patent research rather than regional patent aggregation. They do not request geographic counts, identify leading organizations by region, or generate a regional distribution table. Although these lookups could support broader patent analysis, the supplied chunk does not connect them to the declared geographic workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 96% confidence

Finding

The supplied code requests patent claims for a fixed publication number. It contains no geographic filtering, regional aggregation, organization ranking, or table generation. As shown, claims retrieval is a materially different operation, with no demonstrated supporting role in the declared regional-distribution analysis.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 96% confidence

Finding

The supplied command performs a similar-patent lookup. It does not request geographic grouping, regional counts, leading organizations by region, or a distribution table. Although similarity search could support a broader patent-analysis workflow, the supplied chunk shows no connection to the declared geographic analysis.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence

Finding

The visible command targets an individual patent brief, which is materially different from the declared geographic aggregation workflow. Individual patent retrieval could support a broader analysis, but the supplied chunk shows no connection to regional distribution or user-selected technology. The underlying client implementation is not provided, so no additional behavior is inferred.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence

Finding

The supplied commands demonstrate a candidate-management workflow, including selection decisions for coolant-related patents. They do not show geographic grouping, regional counts, or identification of leading organizations. Although candidate management could support a broader patent-analysis process, this chunk's substantive behavior is not the declared regional-distribution capability. This assessment is limited to the visible commands; the client implementation is not supplied.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence

Finding

General patent search could support the declared regional analysis, but the additional commands expose substantive patent-research capabilities with no demonstrated connection to geographic counts or leading regional organizations. The supplied chunk therefore describes a broader patent-research toolkit than the declared geographic-distribution skill. Because this is a command-reference excerpt, the absence of regional aggregation alone does not prove that the complete skill lacks that functionality.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence

Finding

Patent search could support the declared analysis, but this chunk explicitly describes a feature-based search followed by semantic expansion around the closest patent. That workflow serves similarity discovery, with no demonstrated connection to regional analysis or its promised outputs. The mismatch concerns the supplied workflow, not the Python client invocation or other implementation details.

Content

No source excerpt is available for this finding.

Code capability 'env' detected in scripts/patentmax_client.py but not covered by declared permissions.

High

• Category: MCP Least Privilege
• Confidence: 75% confidence

Finding

The skill uses 'env' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Code capability 'network' detected in scripts/patentmax_client.py but not covered by declared permissions.

High

• Category: MCP Least Privilege
• Confidence: 75% confidence

Finding

The skill uses 'network' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

The workflow sends the user's technology search terms to PatentMax without a privacy disclosure.

Medium

• Category: Output Handling
• Confidence: 90% confidence

Finding

The workflow directs submission of user-derived technology queries to an external patent service without explicitly warning that the query text leaves the user's environment. Although PatentMax is openly identified as the data provider and external searching is necessary for the task, confidential research topics or strategic regional interests could be disclosed if included in those queries.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/api-reference.md (reported line 16)May include surrounding context.

bash

curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
  "https://api.ip930.com/api/patent?pn=CN109761224A"

服务端自己完成内部寻址，这些前置调用不进用户账单。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/api-reference.md (reported line 48)May include surrounding context.

服务端直接返回上次的结果、不再扣费；同一个键换了参数会被拒（400）；上一次还在处理中返回 409。

bash

curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" -H "Idempotency-Key: task42-search-1"   "https://api.ip930.com/api/search?q=%E6%B5%B8%E6%B2%A1%E5%BC%8F%E6%B6%B2%E5%86%B7&ds=cn&size=20"

网络超时、不确定上一次有没有成功时，用同一个键重发，不要换键。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/api-reference.md (reported line 73)May include surrounding context.

curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY"
--data-urlencode 'q=(固态电池 OR 全固态电池) AND 电解质'
--data-urlencode 'ds=all' --data-urlencode 'size=20'
-G "https://api.ip930.com/api/search"

text

> 检索式里有中文和括号，一定用 `--data-urlencode -G`，别手工拼 URL。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/api-reference.md (reported line 89)May include surrounding context.

bash

curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
  "https://api.ip930.com/api/patent?pn=CN109761224A"

某一块上游取不到时，该字段为 null 并在 unavailable 里列出，其余照常返回；

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/api-reference.md (reported line 114)May include surrounding context.

bash

curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
  "https://api.ip930.com/api/claims?pn=CN109761224A"

只要同时需要两块以上，就用 /api/patent——它一口价，拆开单买反而贵。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/faq.md (reported line 35)May include surrounding context.

md

- **密钥复制不全。** 前后有没有多余空格、有没有漏掉尾部字符
- **少了 `Bearer ` 前缀。** 用 curl 时 header 必须是 `Authorization: Bearer pm_live_xxx`，只写密钥不行
- **密钥被撤销了。** 到 [控制台](https://api.ip930.com/features/api-platform)看状态

> 还有个容易踩的：如果请求里带了 `Authorization` 头，URL 上的 `?apikey=` 就不会被读取。两种方式选一种，别混用——带了一个格式错误的 header，正确的 URL 参数也会被忽略。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/faq.md (reported line 41)May include surrounding context.

md

## 402 余额不足

到[控制台](https://api.ip930.com/features/api-platform)充值。

新账户的体验额度分两笔：注册送 ¥10，第一次调用成功后再送 ¥40。如果第二笔一直没到，确认第一次调用确实返回了 200——失败的调用不算。

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/faq.md (reported line 119)May include surrounding context.

md

## 花了多少钱

脚本每次返回都带 `_spent`（本次实扣）和 `_balance`（余额），**这两个数来自服务端，是真值**。
准确的流水到[控制台](https://api.ip930.com/features/api-platform)查。

| 调用 | 单价 |
| --- | --- |

The search workflow lacks a privacy warning about submitting potentially confidential invention details to the patent-search service.

Medium

• Category: Output Handling
• Confidence: 91% confidence

Finding

The workflow directs the agent to turn a user's technical subject, mechanism, and key features into patent-service queries without first checking for confidential invention information or obtaining permission to disclose it. In a patent-search context, those queries could reveal unpublished technical details or commercial research priorities to the service; however, the supplied file does not establish the service's retention practices or demonstrate an actual disclosure.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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/tools.md (reported line 668)May include surrounding context.

试用用完、过期，或想用其他功能（查新、交底书等）时，命令会返回带 "free_trial": true 的错误，message 里写着下一步怎么办（注册 PatentMax 再送 ¥50 体验额度），原样转告用户，不要自己换写法重试。

用户有自己的密钥时用环境变量传，避免写进命令历史；设了就一律用它，不会领试用。密钥在 api.ip930.com 控制台创建：

bash

export PATENTMAX_API_KEY="pm_live_你的密钥"

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/api-reference.md (reported line 124)May include surrounding context.

健康检查

bash

curl -s "https://api.ip930.com/api/v1/health"

不需要密钥，用来确认网络通不通。