Security audit

领域调研

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward bilingual literature-search helper with disclosed browser-based research steps and no bundled executable code.

Before installing, be aware that the skill will send your research keywords to CNKI and Google Scholar and may open a Chrome automation session using a temporary profile. Do not use private or sensitive research terms unless you are comfortable querying those services.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The description requires users to provide Chinese keywords and defines the skill around Chinese/English bilingual output as a fixed behavior. This is a natural-language locale constraint that does not present an opt-in or alternative language choice, which can violate language/locale policy when imposed unconditionally.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.