Verified65% confidenceCautionExact time
Tool poisoning refers to embedding malicious instructions in tool description text that are invisible to humans but interpretable by AI, inducing agents to perform unintended actions.
3
Sources
65%
Confidence
Long-term
Relevance
8/9/2026
First Seen
Sources
Related Claims
UnverifiedThe Agent tool surface is the attack surface.63% similarUnverifiedIn agent or tool-calling scenarios, invisible content such as system prompts, tool definitions, and retrieved documents consumes a large number of tokens.63% similarVerifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.62% similarUnverified提示注入是针对操作型Agent的独特新型攻击向量，恶意网页可通过视觉元素或隐藏文本向Agent注入指令，如何区分真实指令与伪造指令仍是尚未完全解决的开放问题62% similarUnverifiedGoal hijacking is a specific manifestation of prompt injection, in which the attacker overrides the Agent's original goal through injected content so that it performs other tasks.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/717170API
curl https://kongchang.com/api/v1/knowledge/claims/717170MCP
get_claim(id=717170)