专利热点技术

• Outcome: Review
• Latest audit: Oct 21, 2026 · 2:49 AM UTC
• Version: 1.0.0

Overview

The skill fits its patent-analysis purpose, but its handling of saved API keys and redirected requests needs review.

Before supplying a paid key, request HTTPS-only requests, safe redirect handling, and owner-only credential files. Avoid pasting keys into chat. Queries go to PatentMax and may incur the disclosed fees, so omit confidential invention details.

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 (30)

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 PatentMax credential to its API is expected, but this request uses urllib's default redirect handling with an Authorization header. That handling can forward the bearer credential to a different origin following a redirect, allowing an attacker-controlled redirect destination to receive the key; the client also permits an explicitly configured HTTP endpoint.

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 exposes part of an API key rather than performing patent trend analysis. While using an API credential could support the declared purpose, printing its contents is not a necessary or declared part of that functionality. The chunk shows partial credential disclosure, but no transmission to an external destination.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

Search and IPC statistics could support an externally orchestrated hotspot analysis, but this code itself is a broad API client rather than the described analysis workflow. Its statistics command returns one dimension's top 20 results per request; it does not join periods, calculate growth, or generate the promised hotspot table. Its Excel-readable export is instead a candidate-patent ledger. Authentication, billing, and caching are supporting implementation details and are not independently treated as mismatches. 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: 95% confidence

Finding

The visible command's direct objective is finding patents similar to a fixed patent. Although similarity searching could support a broader patent-analysis workflow, the supplied chunk does not connect it to the declared two-period growth analysis. Its demonstrated function therefore materially differs from the declared purpose. No additional resource access or side effects can be established from this command alone.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

Patent retrieval could support the declared analysis, but this chunk describes a distinct proposal-to-similar-patents workflow. Its selection logic is technical similarity, not filing growth. The supplied code therefore does not substantiate the declared primary purpose; no unrelated resource access or additional capabilities are inferred from the unprovided client implementation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

Patent detail and similarity retrieval could support selecting representative patents, but the supplied chunk only investigates one hard-coded patent. It does not implement the defining comparative analysis promised by the description, so its demonstrated primary behavior materially differs from the declared purpose. No unrelated resource access or additional security-sensitive behavior is evident.

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 topic and derived search queries to PatentMax without warning about this external disclosure.

Medium

• Category: Output Handling
• Confidence: 91% confidence

Finding

The workflow directs the agent to begin external searches once the technology field is clear, without explicitly warning that the user's topic and derived queries will be sent to PatentMax. Although the provider and fees are openly identified, the R&D and investment context means queries could reveal confidential research priorities or unpublished technical details; this is a contextual privacy risk, not evidence of malicious exfiltration.

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 sends user-derived technical details to a patent search service without a privacy warning.

Medium

• Category: Output Handling
• Confidence: 90% confidence

Finding

The workflow directs the agent to build external patent-search queries from the user's technical object, mechanism, and distinguishing features without a confidentiality check or disclosure warning. In an R&D and patent-planning context, these inputs may describe unpublished inventions or trade secrets, potentially exposing them to the search provider and its logs. External search is legitimate for this skill, so this is a privacy-safeguard omission rather than evidence of malicious exfiltration; actual exposure depends on the query content and provider data-handling 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 · 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

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 296)May include surrounding context.

python

if _billing["balance_cents"] < 500 and not KEY_FROM_TRIAL:  # 试用用户不提醒，用完时服务端会给注册指引
            out["_balance_warning"] = (
                "余额不足 ¥5，继续批量检索会很快耗尽。"
                "请先提醒用户到 https://api.ip930.com/features/api-platform 充值。"
            )
    if _billing["free_quota"]:
        left = max(0, _billing["free_quota"] - (_billing["free_used"] or 0))

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 357)May include surrounding context.

python

hint = {
            400: "参数有问题，检查必填项和取值范围。",
            401: "密钥无效或已撤销。确认 PATENTMAX_API_KEY 是 pm_live_ 或 pm_test_ 开头的完整密钥。",
            402: "余额不足。到 https://api.ip930.com/features/api-platform 充值。",
            403: "该密钥没有此接口的权限。",
            404: "没找到这篇专利。确认公开号正确且带国别代码，如 CN109761224A。",
            409: "同一个请求上一次还在处理中。等几秒重跑同一条命令即可，不会重复扣费。",

Tainted flow: 'path' from os.environ.get (line 154, credential/environment) → open (file write)

Medium

• Category: Data Flow
• Confidence: 89% confidence

Finding

Caching a trial credential is legitimate, but the file is created with default permissions and contains the credential before chmod restricts access. On a shared system with a permissive umask and traversable cache directory, another local user could read it during this window; the environment-derived path itself is not the vulnerability.

Content

Scanner excerpt · scripts/patentmax_client.py (reported line 157)May include surrounding context.

python

path = _trial_key_path()
    try:
        os.makedirs(os.path.dirname(path), exist_ok=True)
        with open(path, "w", encoding="utf-8") as fh:
            json.dump({
                "api_key": key,
                "expires_at": data.get("expires_at"),

Static analysis

No suspicious patterns detected.