Back to skill

Security audit

学术文献检索(期刊信息、影响因子、下载链接)

Security checks for vulnerabilities and agentic risk

Overview

This is a simple academic paper-search skill whose browser-based search behavior matches its stated purpose, with minor notice and trigger-scope improvements users should understand.

Install only if you are comfortable with a Chinese-language paper-search assistant using your research terms on external academic websites. Avoid entering confidential, unpublished, or personally sensitive research queries unless you intend them to be searched online.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description, triggers, examples, and operating instructions are entirely in Chinese, and the skill does not indicate that users may interact in other languages or opt into a Chinese-only experience. Under the stated policy, a language constraint should either be optional for the user or explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list contains very broad, generic academic phrases such as '找文献', '查论文', and '推荐文献', which are likely to match ordinary user requests beyond narrowly intended use. This increases the chance of unintended invocation and silent routing of user queries to external search behavior, which can cause privacy leakage and surprising tool activation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill states it will use a browser to access external academic databases, but the user-facing description and activation surface do not clearly warn that search terms may be transmitted to third-party sites. Users may disclose sensitive research topics, unpublished ideas, or personal identifiers without realizing their query will leave the local system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.