Back to skill

Security audit

专利分类号

Security checks for vulnerabilities and agentic risk

Overview

The patent-classification workflow fits its purpose, but weaknesses in credential handling and file paths warrant review before use.

Ask the publisher to restrict authenticated requests and redirects to trusted HTTPS destinations and validate patent identifiers before filesystem access. Until corrected, avoid using a valuable API key or running with access to important files. Share only approved technical details, agree a spending limit, and consider whether you want credentials saved locally.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
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
95% confidence
Finding

Sending the PatentMax key to its intended API is legitimate, but this request does not constrain credential-bearing requests to a trusted HTTPS origin. It accepts an arbitrary BASE_URL and uses urllib's default redirect handling, which can forward the explicitly added Authorization header across origins; a malicious or compromised endpoint could therefore expose a paid API credential.

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 IPC classification lookup or generating the declared reference table. Although using an API credential could support patent searches, printing its contents is an undeclared credential-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
96% confidence
Finding

Search, similarity retrieval, IPC statistics, authentication, and caching reasonably support the declared workflow and are not themselves mismatches. However, the code exposes a substantially broader patent-research toolkit, including independent company, citation, legal-event, and image functions. Its implemented spreadsheet-readable export also differs materially from the promised deliverable. Other skill components could potentially supply explanations and assemble the IPC table, but that behavior is not present in this supplied chunk.

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-derived technology queries to PatentMax without warning users about third-party disclosure.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow turns the user's technology description into queries sent to an external patent service without explicitly warning that invention details will leave the local environment. Identifying PatentMax as the data provider makes remote access less surprising, but patent-classification requests can contain unpublished invention details, creating a meaningful confidentiality risk.

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 the user's technical details to the patent-search service.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to derive searches from the user's technical description and submit them to a patent-search service without first checking whether the information is confidential or authorized for external disclosure. In a patent-classification context, combinations of technical features can reveal unpublished inventions or trade secrets even without submitting a complete document. This is a conditional privacy risk, not evidence of malicious exfiltration; searches limited to public information carry substantially less risk.

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

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"),

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
94% confidence
Finding

The environment-configured cache root is not inherently unsafe, but the filename also includes a patent identifier processed by _pn(), which removes spaces and uppercases text without rejecting path separators, absolute paths, or '..'. A crafted --patent value can escape the cache directory during reads and, if the response passes the patent comparison, during JSON writes; patent identifiers are particularly likely to come from agent-consumed external content.

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

The client exposes paid company patent profiling beyond the IPC-classification purpose.

Medium
Category
Excessive Agency
Confidence
91% confidence
Finding

The manifest describes finding IPC codes from technically similar patents and producing classification references. In contrast, do_company() requests an enterprise-wide patent portrait from /api/a/portrait, exposed as a standalone command at L1224–L1226 and treated as billable at L0835; company portfolio profiling is not a direct requirement of choosing IPC classifications.

Content

No source excerpt is available for this finding.