VCPToolBox
VCP 部署在 AI 模型 API 与前端应用之间，通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
0Tools
26Findings
1.8kStars
Mar 22, 2026Last Scanned
9 critical · 15 high · 1 medium · 1 low findings detected
Security Category Deep Dive
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
Findings1
1 critical
criticalJ5Tool Output Poisoning PatternsMCP02-tool-poisoningAML.T0054
Pattern "(return|respond|output).*(?:tool_call|function_call|execute_tool|call_tool|invoke)" matched in source_code: "return res.status(400).json({ status: "error", error: "请求无效，缺少 'schedule_time', 'task_id', 或有效的 'tool_call" (at position 26558)
Tool responses MUST NOT contain instruction-like content, file read directives, or social engineering phrases. Error messages should be factual and technical — never suggest actions involving sensitive data access. See CyberArk ATPA research for attack demonstration.
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
50%2 rules1 found
Injection via prompt templates and runtime tool output