Back to skill

Security audit

胡田 OPC导师 知识产权运营

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese IP monetization decision-support package, but users should treat its legal, tax, valuation, and external data-source guidance as advisory and verify sensitive lookups securely.

Install only if you want Chinese/PRC-focused IP monetization guidance. Do not rely on it as legal, tax, securities, or valuation advice without qualified professionals, and use authenticated HTTPS data sources before sharing patent numbers, deal targets, API credentials, or litigation-sensitive search terms.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
references/00-数据源与实时验证规范.md:15
Finding

Mandatory Patent Verification Uses a Plaintext HTTP Endpoint

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (28)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

该代码块的核心功能非常明确:定义风险评分维度与指标,接收各指标分数,计算维度得分和综合分,映射风险等级,并输出尽调风险评估报告。这与声明中的“知识产权运营变现全流程Skill”存在实质性偏差。声明强调的是面向多种IP商业化路径(许可、转让、入股、质押融资、证券化等)的全量化决策支持,而代码并没有针对这些路径分别建模、比较、推荐或执行任何运营变现决策逻辑。它更像是一个前置的IP尽职调查/风险评估子模块。虽然风险评估可作为运营变现流程中的支持环节,但不足以代表所宣称的主要目的,因此应判定为描述与实际行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明描述的是覆盖知识产权运营变现多路径的综合决策型Skill,范围很广,强调“全流程”“七大路径”“全量化决策”。但提供的代码仅包含许可费率相关计算:按25%法则、增量法、市场比较法计算许可费率,汇总推荐区间,并生成许可报告。没有看到任何与IP转让估值、作价入股、质押融资、证券化、交易结构设计、流程编排或多路径比较决策相关的实现。因此代码只覆盖声明中的“IP许可”这一小部分,且主功能明显更窄,构成实质性描述-行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

声明描述的是一个覆盖多种知识产权运营变现路径的全流程量化决策Skill,范围很广,暗示应包含针对许可、转让、入股、质押融资、证券化等场景的专门分析或决策支持。实际代码则聚焦于单一子能力:知识产权估值。它通过五维度权重体系和成本法/收益法/市场法计算IP价值,并生成估值报告。虽然估值可以作为运营变现中的基础环节,但代码中没有实现七大路径的具体决策、比较、适配性判断、融资/证券化结构分析、流程编排或相关触发机制。因此声明明显宽于实际行为,属于描述与代码能力不匹配。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
77% confidence
Finding

该 markdown 文件以中文撰写,并在规范层面要求“所有定量分析必须引用以下数据源”,整体流程和标注格式也默认采用中文环境与中国知识产权业务语境。文件中未说明这是面向特定中文/中国法域场景的受限技能,也未给出用户语言或地区选择,可能构成自然语言层面的 locale 强制。

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/00-数据源与实时验证规范.md (reported line 111)May include surrounding context.

md
"pageSize": page_size
        }
        
        response = requests.post(url, json=payload, headers=headers)
        data = response.json()
        
        # 数据标注格式

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/00-数据源与实时验证规范.md (reported line 143)May include surrounding context.

md
"pageSize": page_size
        }
        
        response = requests.post(url, json=payload, headers=headers)
        data = response.json()
        
        # 数据标注格式

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/00-数据源与实时验证规范.md (reported line 167)May include surrounding context.

md
"pageSize": page_size
        }
        
        response = requests.post(url, json=payload, headers=headers)
        data = response.json()
        
        # 数据标注格式

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/00-数据源与实时验证规范.md (reported line 191)May include surrounding context.

md
"pageSize": page_size
        }
        
        response = requests.post(url, json=payload, headers=headers)
        data = response.json()
        
        # 数据标注格式

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The section presents aggressive IP enforcement tactics such as '诉讼威胁' as operational strategy without cautionary framing, legal boundaries, or compliance guidance. In a decision-support skill for IP monetization, this can normalize coercive or legally risky conduct and may encourage users to apply pressure tactics without consulting qualified counsel or assessing antitrust, abuse-of-rights, or unfair competition risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill content, including headings, instructions, scoring criteria, and report template, is presented only in Chinese, which effectively forces a single language/locale for use. The file does not state that the skill is region-specific or offer an opt-in or alternative language, so it creates a natural-language locale constraint under the policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file is written entirely in Chinese and presents the reporting template, labels, and recommendations only in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest describes a skill for '知识产权运营变现全流程' covering licensing, transfer, equity contribution, pledge financing, and securitization decisions. This file instead provides detailed guidance on infringement enforcement, compensation calculation, invalidation strategy, evidence preservation, and litigation ROI, which are legal dispute-response topics rather than monetization/operation pathways.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown skill contains all headings, instructions, and examples exclusively in Chinese, and nowhere indicates that use of Chinese is optional or limited to a China-specific audience. Under the language/locale policy, forcing a single language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains natural-language descriptions and user-facing text primarily in Chinese, including the module docstring and later output strings, but it does not indicate that Chinese is optional or that the tool is intentionally limited to a Chinese-speaking or China-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains natural-language descriptions and user-facing report/output strings primarily in Chinese, such as the module description and generated report labels. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This Python file contains natural-language documentation and labels that predominantly enforce Chinese for the skill’s interface and explanations, despite only a brief English title being present. Under the policy, forcing a specific language without user opt-in is a locale/language policy 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 report generator returns headings, labels, and valuation summaries entirely in Chinese, which constrains all users to a single locale. Because there is no opt-in, fallback, or documented regional limitation, this conflicts with the stated language/locale policy requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire template is written in Chinese and specifies PRC law, but the file does not state that it is intended only for Chinese-language or China-jurisdiction use, nor does it offer an alternative language or user choice. Under the policy, forcing a specific language/locale without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document is presented entirely in Chinese from the title onward, and later specifies PRC law as the governing law. For a general-purpose template file, this imposes a language/locale choice without opt-in or an explicit statement that the template is intended only for China-specific use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The user-facing documentation is entirely in Chinese, including the title, description, and usage instructions, with no indication that other languages are supported or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, a skill that effectively forces a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file’s user-facing description and instructions are consistently presented only in Chinese, including operational guidance and warnings. Under the policy rule, forcing a specific language without user opt-in or a documented locale justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document gives specific tax formulas, preferential treatment descriptions, and transactional decision guidance in a way that can be read as actionable advice, while the disclaimer that professional review is needed appears only at the very end. In a skill intended to support quantitative decision-making for IP monetization, users may rely on these rules without noticing jurisdictional limits, policy changes, or deal-specific exceptions, leading to legal, tax, or financial mistakes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file uses Chinese throughout and does not indicate that users may request another language or locale. Under the policy rule for natural-language constraints, forcing a single language without opt-in can be a locale-policy issue when no justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and guidance only in Chinese, with no indication that the user can choose another language or that the content is intentionally limited to a Chinese-speaking or China-specific audience.

Content

No source excerpt is available for this finding.