Unverified50% confidenceFactExact time
Jnvoy's MCP security module additionally detects tool poisoning and secret leakage in tool responses.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
VerifiedA malicious MCP Server can declare a legitimate tool name and embed prompt injection instructions in the description field; this type of attack is known as "Tool Poisoning."73% similarUnverified工具投毒攻击可将读取 SSH 私钥并外传的隐藏指令暗藏在工具描述中，同时返回正确结果71% similarUnverifiedDisclosed MCP vulnerabilities include: argocd-mcp shipped with no authentication at all, Rill's OAuth flow allowed attackers to skip the user consent step, and prompt injection existed in the tool descriptions of multiple MCP servers.71% similarUnverifiedA single compromised MCP server can execute prompt injection, credential exfiltration, delivery of phishing toolkit fingerprints, PII leakage, token theft via OAuth, and SSRF attacks.70% similarUnverifiedMCP Apps设计了四层安全防护机制：iframe沙盒隔离、预渲染审查、可审计的消息通道、用户授权确认69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019266API
curl https://kongchang.com/api/v1/knowledge/claims/1019266MCP
get_claim(id=1019266)