Back to skill

Security audit

企业尽调报告

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly purpose-aligned, but it generates HTML reports from public web data without clear sanitization or privacy-use safeguards.

Install only if you are comfortable generating China-focused due-diligence reports from public records. Treat the output as sensitive and potentially incomplete; verify important claims against primary sources, avoid unnecessary personal data exposure, and ensure generated HTML is escaped or sanitized before opening or sharing reports.

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
assets/report-template.html:151
Finding

Unescaped External Data Inserted into Generated HTML Reports

Content
View full analysis
{{COMPANY_NAME}} — 企业调查报告 ``` ```html
企业尽职调查报告

{{COMPANY_NAME}}

{{COMPANY_NAME_EN}}
报告日期:{{REPORT_DATE}}
数据来源:国家企业信用信息公示系统 / 企查查 / 爱企查 / 天眼查 / 启信宝
报告性质:公开信息整理 · 仅供参考
``` ```html {{REGISTRATION_ROWS}}
``` ```html

📜 二、经营范围

{{BUSINESS_SCOPE}}

👥 三、股东及股权结构

{{EQUITY_STRUCTURE}}

👤 四、实际控制人与最终受益人

{{ACTUAL_CONTROLLER}}

👥 五、主要管理人员

{{MANAGEMENT}}

📞 六、联系方式与公开信息

{{CONTACT_INFO}}

⚠ 七、风险全景分析

{{RISK_ANALYSIS}}

🔄 八、历史变更记录

{{CHANGE_RECORDS}}

Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to activate on generic requests like querying or analyzing a company, which can cause the skill to run unexpectedly and collect or synthesize sensitive corporate and personal risk information without clear user intent. In this skill’s context, unintended activation is more dangerous because the output includes legal, ownership, and individual risk profiling data aggregated from multiple public sources.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to collect, aggregate, and present sensitive personal and corporate risk information, including legal cases, shareholder relationships, actual controllers, and high-consumption restrictions, but provides no warning or usage constraints to the user. This increases the chance of privacy-invasive profiling, reputational harm, or misuse of partially accurate public data, especially when combining multiple sources into a single report that appears authoritative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The HTML root sets lang="zh-CN", which hard-codes a specific language/locale for the generated report. Under the policy, forcing a locale without user opt-in or clear justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill file is written only in Chinese and provides no indication that users may choose another language or that the skill is limited to a China-specific compliance or reporting context. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The file presents the skill entirely as a China-specific, Chinese-language reporting workflow and includes Chinese-only trigger phrases and output expectations, but it does not state that this locale is optional or user-selected. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern unless the restriction is explicitly justified and documented.

Content

No source excerpt is available for this finding.