Back to skill

Security audit

AI大模型专家|API中转与Token Hub企业网关

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language planning guide for secure AI API gateway and token management work, with no executable code or hidden authority.

Install this skill if you want Chinese-language guidance for designing an authorized AI API gateway or token hub. Review the resulting architecture carefully because real deployments will handle sensitive tokens, billing, tenant boundaries, logs, and upstream contracts, but the skill itself does not add executable code or hidden access.

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
  • 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
95% confidence
Finding

The display name, short description, and default prompt are all written exclusively in Chinese, which indicates a fixed language/locale experience. There is no visible opt-in, alternative language option, or documentation that this skill is intentionally restricted to Chinese users or a China-specific context.

Content

No source excerpt is available for this finding.