ClawHub
Back to skill

Security audit

专利趋势分析

Security checks for vulnerabilities and agentic risk

Overview

The patent-analysis workflow is coherent, but its API-key handling needs review before use.

Queries go to PatentMax and may incur disclosed charges. Use nonconfidential search terms. Before supplying a paid key, require HTTPS-only authenticated requests, safe redirect handling, and private credential storage; avoid sending keys through chat.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden 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

The client attaches its API bearer token to requests without enforcing an HTTPS endpoint or restricting credential forwarding during redirects. Python's default urllib redirect handling can preserve this Authorization header when following a redirect to another origin, exposing the key if the API or an intermediary redirects to an attacker-controlled destination; an HTTP endpoint override also sends it without transport encryption.

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 code exposes part of an API key rather than analyzing patent trends or producing the declared reports. Although accessing an API key could support patent-data retrieval, printing its value is not necessary for that purpose and constitutes an undeclared credential-disclosure behavior. No network transmission is shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The yearly and applicant statistics can support the declared workflow, but the supplied code is substantially broader than a trend-analysis tool and does not itself deliver several promised analyses or outputs. Its statistics command returns one dimension's top 20 values, leaving longitudinal comparison and entrant detection to external orchestration. Authentication, API access, caching, billing controls, and ordinary output-file handling are supporting implementation details and are not independently treated as mismatches.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied commands focus exclusively on investigating one fixed patent. They do not perform year-by-year aggregation, applicant-change analysis, new-entrant identification, or trend-table generation. Patent retrieval could support a broader trend workflow, but this chunk provides no connection to those declared outputs and instead implements a materially different patent-investigation workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied command performs a similar-patent lookup. It shows no annual aggregation, growth-stage analysis, applicant tracking, new-entrant identification, or trend-table export. Similarity search could support a broader analysis workflow, but the supplied chunk alone implements a materially different primary operation from the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk targets a fixed patent's claims, not annual filing counts, applicant changes, or new entrants. It contains no visible trend aggregation or table generation. Authentication and API access are ordinary implementation details; the mismatch is the substantive data retrieval performed. 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

The supplied command requests a brief for one specific patent. It shows no collection or aggregation of filings across years, applicant comparisons, new-entrant identification, or trend-table generation. Although patent retrieval could support a broader workflow, no such connection is evident in this chunk. The client implementation is not supplied, so its internal behavior cannot be verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Patent searching could support the declared analysis, but the supplied workflow specifically targets the closest patent to a solution and expands to similar patents. It contains no temporal aggregation, applicant-entry analysis, growth-stage assessment, or trend-table generation. Thus, the visible workflow is directed toward technical similarity searching rather than the declared trend-analysis purpose. This assessment is limited to the supplied chunk; the client implementation is not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Patent search is a reasonable supporting operation for the declared trend analysis. However, the supplied commands also expose distinct patent-inspection, similarity, citation, and illustration-retrieval capabilities that are not described in the declared purpose or connected here to producing trend tables or new-entrant lists. This is a scope mismatch, not evidence of malicious behavior. Because the chunk is a command-reference document rather than the client implementation, the assessment is limited to the operations explicitly 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 the user's technology search terms to PatentMax without a privacy disclosure.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

These steps instruct the agent to build a query from the user's technology direction and submit it to PatentMax for search and statistics. Although the skill identifies PatentMax as the data source and discloses costs, it does not warn that the user's query—which may reveal confidential research or investment interests—is transmitted to a third-party service.

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 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 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。

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

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow directs the agent to construct provider-bound searches from technical objects, mechanisms, and distinguishing features without first checking whether those details are confidential. In patent research, these inputs may describe unpublished inventions or proprietary R&D, so following the workflow could disclose sensitive information to an external provider; searches using only public technical information would carry substantially less risk. The supplied file does not establish the client's actual transmission behavior or the provider's retention practices.

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。

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/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
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/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 |
| --- | --- |

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