Back to skill

Security audit

intelligence-analyst-claw

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language research assistant skill that uses normal web research workflows and simple local helper scripts, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install this only if you want a Chinese-language research workflow. Before using it with paid or logged-in databases, confirm which account or source should be accessed and avoid using it on unauthorized internal materials. Treat investment and market outputs as research support, not professional financial advice.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

该描述与代码行为存在明显不匹配。描述将技能定位为覆盖行业研究、投资分析、政策追踪、技术评估、市场情报等多个场景的综合情报分析师;但给出的代码只是一个辅助解析器,依赖外部先获取财报文本,然后用正则抽取有限的财务字段并输出表格。它既不执行信息收集,也不做趋势分析、竞争格局分析、投资判断、政策影响评估或技术可行性分析。虽然“公司投资价值评估”可能会用到财务数据提取作为支持步骤,但当前代码只是非常狭窄的底层工具,不能代表声明中的主要能力,因此应判定为描述与实际行为不一致。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common user requests such as general analysis, reports, or industry questions, which can cause the skill to activate in contexts the user did not specifically intend. Overbroad activation increases the chance of unnecessary web access, collection of external data, or use of specialized workflows that may expose private context or produce unvetted outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs use of browser and web tools, including handling pages that may require login, but provides no user-facing warning or consent gate around account access, session usage, or retrieval of potentially sensitive data. In context, an intelligence/research skill is especially prone to aggregating large amounts of data from multiple sources, so silent access to logged-in resources could expose private, subscription-only, or organizational information beyond the user's expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This file contains user-facing natural-language guidance exclusively in Chinese, including headings, descriptions, and search templates. Under the policy, forcing a specific language without user opt-in or an explicit justification can be a language/locale 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 module docstring is entirely in Chinese and describes the script's intended agent usage only in that language. This imposes a specific language/locale without offering user opt-in or documenting a justified region-specific constraint, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The generated plan hard-codes Chinese search phrases and Chinese-specific report sources, and the returned instructions are also in Chinese. Because the skill does not offer a language/locale selection or explain that it is intentionally limited to a Chinese-market context, this is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all skill content in a single language variant and does not indicate that the user can choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring is entirely in Chinese and describes the script's behavior and usage only in that language. The function also hard-codes Chinese labels and example values, indicating a language-specific experience without any user opt-in or documented locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Lines L03-L04 describe the script purpose and usage exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation, and there is no indication here that users may choose another language or that the Chinese-only constraint is required.

Content

No source excerpt is available for this finding.