Back to skill

Security audit

My PubMed Search

Security checks for vulnerabilities and agentic risk

Overview

This PubMed search skill is purpose-aligned and does not show hidden persistence, credential theft, destructive behavior, or unrelated access.

Install only if you are comfortable with a Chinese-oriented PubMed helper that sends search queries to NCBI/PubMed. Expect to adjust the documentation or command examples because the artifact references PowerShell scripts that are not included, while the included implementation is Python.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
79% confidence
Finding

整体上代码与 PubMed 文献检索这一核心用途是相关的,但声明与实际行为并不完全一致。声明强调“简易PubMed搜索”以及“使用web搜索和API调用”,而实际代码没有实现任何 web 搜索,只使用了 NCBI E-Utilities API。除此之外,代码不仅搜索 PMID,还进一步抓取文献详细信息(标题、摘要、作者、期刊、年份、DOI)并提供多种参考文献格式化输出,这些属于额外能力,且未在声明中体现。虽然这些能力仍围绕 PubMed 文献处理,不是完全无关功能,但按评估标准,属于未声明的重要能力和资源/实现方式不一致,因此应判定为存在描述与行为不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill instructs use of network-capable tooling and external API access but does not declare any tool scope such as allowed-tools or permissions. This creates an authorization and governance gap: an agent may invoke broader network capabilities than reviewers or runtime policy expect, increasing the chance of uncontrolled outbound requests or misuse of user-supplied queries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template is entirely in Chinese and presents fixed Chinese headings and output structure without any indication that language should follow the user's preference. In a general-purpose agent skill, forcing a specific language can cause misleading or unusable output, reduce transparency, and violate expected user-control or accessibility requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill file is written in Chinese, while also presenting search-language options like English, Chinese, and Japanese, but it does not offer the user a choice of interaction language or explain that the skill is intended only for a Chinese-speaking context. This can violate language/locale policy when users are implicitly forced into a specific language without opt-in.

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 contains end-user instructional content exclusively in Chinese, and there is no note that the skill is region-specific or that users may choose another language. Under the stated 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

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This is a natural-language policy issue because the file presents its description and operational text in Chinese only, which can force a specific language on users without opt-in. The file does not indicate that the skill is region-specific or provide any alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file presents its heading and format labels only in Chinese, which can impose a language/locale constraint on users without any explicit opt-in. The policy specifically calls for flagging cases where a skill forces a specific language without user choice or justification.

Content

No source excerpt is available for this finding.