Unverified50% confidenceFactExact time
The attack in which a server silently changes tool definitions after being trusted is referred to by researchers as Tool Poisoning.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA 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."79% similarUnverified在具备工具调用能力的 Agentic 系统中，一次成功的提示注入可能导致数据泄露、恶意代码执行甚至供应链攻击69% similarUnverifiedToolport 会对 Rug-pull 和 Tool poisoning 两类攻击风险进行标记，并支持破坏性操作等待用户批准后再执行69% similarUnverified数据投毒攻击中，清洁标签攻击允许攻击者在不修改样本标签的情况下植入后门，特洛伊木马攻击通过特定触发词激活预设的恶意行为68% similarUnverifiedDirectly executing Skill code downloaded from the internet or autonomously generated by an agent in the host environment poses security risks, as it may contain dangerous operations such as deleting files, accessing sensitive directories, or launching network attacks.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/956099API
curl https://kongchang.com/api/v1/knowledge/claims/956099MCP
get_claim(id=956099)