Back to skill

Security audit

全球专利检索 · PatentMax

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PatentMax patent-search integration that uses a paid external API and local result files, with no artifact-backed evidence of hidden execution, credential theft, persistence, or destructive behavior.

Install only if you are comfortable using a paid PatentMax API key and sending patent queries to api.ip930.com. Treat invention descriptions, formulas, source code, and unpublished business details as sensitive; redact them or get explicit approval before searching. Store the API key in a private environment or secret store, avoid committing MCP configs with Authorization headers, and verify PATENTMAX_BASE_URL is not set to an unexpected host.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (42)

Tainted flow: 'req' from os.environ.get (line 199, 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 210)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,

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The installation guide repeatedly instructs users to place a live API key directly into shell commands, Authorization headers, and MCP config examples without warning about shell history, process lists, pasted config persistence, or accidental sharing. In an agent/tooling context, these examples increase the chance that a real production credential is exposed to logs, screenshots, transcripts, or committed configuration files.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
81% confidence
Finding

This example sends a bearer token to an external service and encourages direct command-line use with a production key. In isolation that is normal API usage, but in an agent skill context it increases the risk of credential exposure through terminal history, execution logs, or captured transcripts while authorizing outbound transmission to a third party.

Content

Scanner excerpt · INSTALL.md (reported line 79)May include surrounding context.

bash
curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
  --data-urlencode 'q=固态电池' --data-urlencode 'size=5' \
  -G "https://api.ip930.com/api/search"

检索式里有中文和括号时,务必用 --data-urlencode -G,别手工拼 URL。

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

This example transmits the bearer token to retrieve full patent content from an external endpoint. While aligned with the product's purpose, the documentation normalizes use of live credentials in plain command examples without addressing logging and persistence risks, which can lead to credential leakage in shared or agent-executed environments.

Content

Scanner excerpt · INSTALL.md (reported line 88)May include surrounding context.

bash
curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
  "https://api.ip930.com/api/patent?pn=CN109761224A"

各客户端

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The MCP configuration example embeds an Authorization header containing a live-key format directly inside JSON configuration. This creates a strong risk of long-lived credential exposure through config files, sync services, screenshots, support bundles, or accidental source control commits, especially because the document explicitly recommends production keys.

Content

Scanner excerpt · INSTALL.md (reported line 105)May include surrounding context.

md
{
  "mcpServers": {
    "patentmax": {
      "url": "https://api.ip930.com/api/mcp",
      "headers": { "Authorization": "Bearer pm_live_你的密钥" }
    }
  }

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill description and user-facing instructions are written only in Chinese, including setup, usage, limitations, and warnings. Under the stated policy, a skill that effectively requires a specific language without user opt-in can be a language/locale policy violation unless the locale constraint is explicitly justified, which is not done here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation description says to use the skill when the user mentions broad phrases like “找专利”, “现有技术”, “某个领域谁在申请”, or directly provides a patent/publication number. Several of these are common intents that could arise in general discussion, and the file does not provide exclusion conditions or negative examples to clarify when the skill should not trigger.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Earlier guidance says that on key failure the agent must stop and must not switch to public web patent search to complete the answer, reinforcing that this skill's workflow is centered on PatentMax results. Later, the document explicitly instructs using external browsing tools to query CNIPA/WIPO/EPO/USPTO and other external sources, which contradicts that earlier intent and the stated 'direct PatentMax' positioning.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The skill sends user patent queries and possibly sensitive pre-filing technical descriptions to an external PatentMax service. Because the skill itself warns that user technical方案 will be transmitted server-side, this creates a genuine external-transmission risk if users provide confidential trade secrets, unpublished invention details, or other sensitive data without clear consent.

Content

Scanner excerpt · SKILL.md (reported line 670)May include surrounding context.

python "$DIR/scripts/patentmax_client.py" --help

text

通过环境变量传密钥,避免写进命令历史。密钥在 [api.ip930.com](https://api.ip930.com/features/api-platform) 控制台创建。

**每天前 30 次 `search` / `brief` 免费**(生产密钥,北京时间零点重置),用完自动转为正常计费。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instructions state that error message is user-facing Chinese text and must be relayed verbatim. This imposes a specific language on user-facing communication without indicating opt-in, fallback, or a user language preference, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs use of external browsing tools and third-party registries for broader research that is not reflected in the manifest description. This can cause unintended data exfiltration and trust-boundary violations, because user queries or sensitive technical details may be sent to additional services the user did not expect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This file imposes a single language for the skill guidance without any opt-in, alternative language option, or justification that the skill is region-specific. Under the policy, forcing a specific language without user choice is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring explicitly states that errors and human-readable prompts are returned in Chinese, and the rest of the CLI help/messages are also hard-coded in Chinese. For an all-purpose patent client, this is a natural-language locale constraint without user opt-in, which matches the policy category for language/locale violations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest explicitly says the skill covers downloading patent PDFs, but in this client the implemented subcommands include search, stats, company, brief, similar, citation, figure, budget, candidates, and read. Although pricing metadata includes pdf, there is no corresponding command or API call in this file, so the described capability is not actually present here.

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 · INSTALL.md (reported line 7)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · INSTALL.md (reported line 71)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · INSTALL.md (reported line 99)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · INSTALL.md (reported line 134)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · README.md (reported line 100)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · README.md (reported line 110)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · references/api-reference.md (reported line 16)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · references/api-reference.md (reported line 48)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · references/api-reference.md (reported line 73)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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 · references/api-reference.md (reported line 89)May include surrounding context.

md
if _billing["balance_cents"] < 500:
            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))