Verified65% confidenceFactExact time
A 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."
3
Sources
65%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedThe attack in which a server silently changes tool definitions after being trusted is referred to by researchers as Tool Poisoning.79% similarUnverifiedCritics point out that an MCP Server with file system write permissions, once exploited by malicious tools, would present an attack surface harder to audit than traditional API integrations71% similarVerifiedPrompt injection attacks induce AI agents to execute malicious operations by embedding text disguised as system instructions in code comments, documentation, web content, or even file names.70% similarPartially VerifiedOne of the security risks of MCP is prompt injection attacks, where malicious data sources may embed instructions in returned content to induce the model to perform unauthorized operations.70% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/533743API
curl https://kongchang.com/api/v1/knowledge/claims/533743MCP
get_claim(id=533743)