上市前专利排查

• Outcome: Review
• Latest audit: Oct 21, 2026 · 3:40 AM UTC
• Version: 1.0.0

Overview

The skill performs its advertised patent checks, but verified weaknesses in credential protection, file handling, and search-result validation warrant review.

Seek a version that fixes credential routing, cache containment, and response validation before using a paid key or confidential product details. Prefer a limited-use key supplied outside chat, approve the search terms sent to PatentMax, and review spending limits. Treat the output as preliminary screening, not legal clearance.

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 (28)

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

Authenticating to the intended patent API is legitimate, but the bearer token is attached without enforcing HTTPS or restricting destinations. The default urllib redirect handling can forward this explicitly added Authorization header to another origin, so a malicious redirect or an untrusted base-URL configuration can expose the saved paid-account key and confidential prelaunch search 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 shell command does not search patents or generate a screening list. Although using a patent-service API key could support the declared purpose, printing part of that secret is not necessary authentication behavior and is not disclosed by the description. The shown code exposes a credential prefix; it does not demonstrate external transmission.

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 prelaunch product details to PatentMax without warning the user about this disclosure.

Medium

• Category: Output Handling
• Confidence: 94% confidence

Finding

The workflow turns prelaunch product names and detailed functional or structural features into queries submitted to PatentMax, without explicitly warning that those details leave the user's environment or checking authorization to disclose them. Although the external data provider is identified, the prelaunch context makes these queries potentially confidential and capable of revealing unreleased designs or commercial plans.

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/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 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。

The workflow submits details of the user's technical proposal to a patent-search service without a privacy warning.

Medium

• Category: Output Handling
• Confidence: 90% confidence

Finding

The workflow directs the agent to construct patent-service queries from the user's technical object, mechanism, and distinguishing features, without first checking whether those details are confidential or warning about external disclosure. In a prelaunch patent-screening context, these queries may expose unpublished inventions or commercially sensitive product plans to the search provider; the supplied file does not establish how that provider handles or retains queries. This appears to be an omitted privacy safeguard rather than deliberate 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/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 verbatim Chinese error messages without offering a user-language alternative.

Medium

• Category: Output Handling
• Confidence: 94% confidence

Finding

The file defines error messages as Chinese-language explanations and instructs the agent to relay them verbatim. This requires Chinese user-facing output even when the user prefers another language, without an opt-in or a documented reason for that 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 · 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

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: 65% confidence

Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

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"),

Unrecognized response structures can still be reported as zero patent results despite the documented fail-closed behavior.

Medium

• Category: Excessive Agency
• Confidence: 99% confidence

Finding

require_rows() accepts any dictionary containing a list, while rows_of() can return an empty result for an unrelated empty list or discard every non-object element. Consequently, malformed or changed API responses can become apparent zero-hit searches, which is particularly dangerous when a prelaunch patent screening may interpret missing results as reduced legal risk.

Content

No source excerpt is available for this finding.

Tainted flow: '_ledger_path()' from os.environ.get (line 461, credential/environment) → open (file write)

Medium

• Category: Data Flow
• Confidence: 65% confidence

Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/patentmax_client.py (reported line 477)May include surrounding context.

python

def _save_ledger(ledger):
    try:
        with open(_ledger_path(), "w", encoding="utf-8") as fh:
            json.dump(ledger, fh, ensure_ascii=False)
    except OSError:
        pass

Tainted flow: '_patent_cache_dir()' from os.environ.get (line 673, credential/environment) → open (file write)

Medium

• Category: Data Flow
• Confidence: 95% confidence

Finding

The environment-selected cache root is legitimate, but the complete filename also includes a patent identifier processed by _pn(), which leaves slashes, backslashes, and '..' intact. An identifier influenced by untrusted input can escape the task cache during reads or writes, enabling cache poisoning or unintended JSON-file access or overwrite; patent-number comparison does not enforce safe filesystem syntax.

Content

Scanner excerpt · scripts/patentmax_client.py (reported line 697)May include surrounding context.

python

return
    try:
        os.makedirs(_patent_cache_dir(), exist_ok=True)
        with open(os.path.join(_patent_cache_dir(), _pn(pn) + ".json"), "w", encoding="utf-8") as fh:
            json.dump(whole, fh, ensure_ascii=False)
    except OSError:
        pass

Static analysis

No suspicious patterns detected.