Back to skill

Security audit

Academic Search Zh

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese academic literature-search helper with no executable code or hidden high-impact behavior.

Safe to install for Chinese academic literature-search support. Review whether you want this skill to activate on broad research-writing prompts, and avoid sharing copyrighted paywalled full texts unless you have rights to use them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written entirely in Chinese and frames itself as a Chinese-language assistant without stating that language should follow user preference. This can override user language expectations, reduce transparency, and create a mild routing/control issue where users receive responses in an unintended language, especially when the skill is auto-invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes very broad trigger phrases such as general academic help, literature review, research positioning, and paper-finding requests that overlap heavily with normal assistant usage. This can cause the skill to activate unintentionally for generic user queries, increasing prompt-surface exposure and the chance that users are routed into skill-specific behavior without clear consent or need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.