Back to skill

Security audit

AI大模型专家|便携AI聚合API 替代方案|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese-language workflow for comparing API billing and generating a local migration plan, with no hidden network access, persistence, or credential-stealing behavior found.

Install this only if you want a Chinese-language AI-HIVE comparison workflow. Before using it for real migration decisions, verify current provider prices and terms, use non-production samples first, keep API keys in environment variables, and choose the generated JSON output path deliberately.

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill instructs users to run a local script that writes an output file (invoice-reconcile-plan.json), but the skill does not declare any tool scope such as permissions or allowed-tools. That mismatch weakens least-privilege controls because a host system or agent may permit file-writing behavior implicitly rather than through explicit policy, making it easier for a modified or extended version of the skill to write unexpected files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file presents user-facing metadata primarily in Chinese on L2-L3, but the default prompt on L4 is hard-coded in English. This can create a language-policy issue because the skill appears to impose a language choice without documenting user opt-in or offering alternatives.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script's docstring, CLI argument descriptions, checklist labels, metrics, and decision text are all hard-coded in Chinese. This creates a language/locale constraint for users of the skill without any opt-in, fallback, or documented justification that the skill is limited to a Chinese-speaking or region-specific context.

Content

No source excerpt is available for this finding.