专利授权周期

• Outcome: Review
• Latest audit: Oct 20, 2026 · 11:25 AM UTC
• Version: 1.0.2

Overview

The patent-timing workflow is implemented, but credential protection and cache file handling need review before use.

Before supplying a paid API key, request HTTPS-only approved destinations, safe redirect handling, and contained cache filenames. Prefer protected local credential configuration over pasting keys into chat. Searches send terms to PatentMax and may incur disclosed charges; use broad public terms and set a spending limit. Publisher identity could not be independently verified from the empty metadata or inaccessible public pages.

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 (34)

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: 95% confidence

Finding

Sending the API key to the intended PatentMax service is legitimate, but this function attaches it to an unrestricted environment-configured URL and uses urllib's default redirect handling. An attacker-controlled endpoint configuration or cross-origin redirect can disclose the bearer credential; an HTTP override also removes transport protection, potentially exposing a paid account and its queries.

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 retrieve patent records, calculate grant timelines, or produce a statistics table. Instead, it exposes part of an API credential. Although using an API key could support patent data retrieval, printing the key's prefix is an undeclared credential-disclosure behavior rather than an implementation step necessary for the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

The supplied code is a broad patent-research client rather than the specialized grant-cycle analyzer described. Search could provide inputs for a separate grant-cycle workflow, but this chunk does not select recently granted patents as a dedicated operation or compute any elapsed-time statistics. Its stats command returns categorical Top-20 distributions, and its Excel-compatible CSV contains candidate records without grant dates or duration metrics. Credential handling, caching and billing are supporting implementation details, not the basis for this mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence

Finding

The supplied request targets a claims endpoint for one fixed patent publication. It does not show retrieval of filing and grant dates, selection of recently granted patents by field, duration calculations, or table generation. Although authenticated patent API access could support the declared workflow, this particular claims lookup does not have a demonstrated connection to grant-cycle analysis. This assessment is limited to the supplied code chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 93% confidence

Finding

Patent searching and bibliographic retrieval could support the declared duration analysis. However, semantic similarity, citation exploration, full-text review, and figure downloads are broader patent-research capabilities not represented by that purpose. The visible chunk therefore exposes materially broader functionality. This assessment is limited to the supplied command examples; the client implementation and any duration-analysis workflow elsewhere are not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

The supplied commands implement patent research and similarity lookup, not the declared grant-cycle analysis. They show no selection of recently granted patents, extraction of filing and grant dates, duration calculations, or spreadsheet export. Although patent retrieval could support a broader statistical workflow, this chunk does not establish that connection and instead presents a materially different research workflow. This assessment is limited to the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 90% confidence

Finding

Patent retrieval could support the declared analysis, but the supplied workflow specifically focuses on finding technically similar patents. It does not select recently granted patents, extract filing and grant dates, calculate authorization durations, or generate a statistics table. The shown workflow therefore has a materially different operational focus. This assessment is limited to the supplied commands; the referenced client's implementation is not shown.

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 user-supplied technical terms and search filters to PatentMax without warning that these inputs leave the local environment.

Medium

• Category: Output Handling
• Confidence: 92% confidence

Finding

The workflow places user-provided technical terms and optional filters into queries for an external PatentMax service without an explicit outbound-data notice or confidentiality check. In a pre-filing patent-planning context, those terms can reveal unpublished invention details or business interests; identifying PatentMax as the data source reduces concealment concerns but does not clearly explain that user inputs are transmitted to it.

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 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/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/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 workflow expands grant-time statistics into substantive patent analysis using additional paid queries.

Medium

• Category: Excessive Agency
• Confidence: 91% confidence

Finding

The manifest promises filing-to-grant timing statistics for planning. L029–L042 instead prescribe full-text, citation, and similarity queries to understand individual patents, while L060 explicitly promotes prior-art discovery, competitor benchmarking, and novelty assessment. These are separate analytical objectives, not necessary implementation details of calculating grant-time statistics, and the workflow states that the three-query sequence costs ¥0.25.

Content

No source excerpt is available for this finding.

The workflow sends user-derived technical search terms to a patent-search service without warning about disclosure of potentially confidential invention details.

Medium

• Category: Output Handling
• Confidence: 88% confidence

Finding

The workflow directs the agent to construct external patent searches from the user's technical subject, mechanism, and distinguishing features without first checking whether those details are confidential. If a user supplies an unpublished invention, those queries could disclose sensitive technical combinations to the search provider; estimating grant times generally needs only broad field-level terms, making this additional specificity avoidable.

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"

Requires Chinese error messages to be relayed verbatim without a user language choice.

Medium

• Category: Output Handling
• Confidence: 94% confidence

Finding

Line 701 specifies that user-facing error messages are in Chinese, and lines 703–705 require relaying those messages unchanged. This forces Chinese output even for users communicating in another language, without an opt-in or a documented justification for the language restriction.

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 · 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。

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/patentmax_client.py (reported line 102)May include surrounding context.

python

# 设了 PATENTMAX_API_KEY 就一律用它，不会去领试用。
TRIAL_SOURCE = "patent-search-cn"
TRIAL_GROUP = "patent-search"
TRIAL_REGISTER_URL = "https://api.ip930.com/features/api-platform"
KEY_FROM_TRIAL = False