Back to skill

Security audit

AI大模型专家|多模型成本路由中心|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Chinese-language workflow aid for planning AI model routing migrations, with only a small disclosed local JSON plan generator and no evidence of hidden, destructive, or credential-stealing behavior.

Before installing, confirm you are comfortable with a Chinese-language workflow that may open AI-HIVE documentation and can generate a local routing-policy-plan JSON file. Keep any real provider keys in environment variables as instructed, use non-production samples first, and review the generated plan before using it for production routing decisions.

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
  • 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
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill instructs the user to run a local script that writes an output JSON file, but the skill metadata does not declare any tool scope such as permissions or allowed-tools. This creates a capability/manifest mismatch: reviewers and enforcement systems cannot reliably tell that file-write behavior is intended, which weakens least-privilege controls and could allow unexpected filesystem side effects if the skill is executed by an agent runtime.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file's natural-language description and CLI help strings are entirely in Chinese, including the module docstring and argument descriptions. This imposes a specific language/locale on users without any opt-in or documented reason that the skill is region-specific, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.