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% similarUnverifiedPrompt injection is a novel and unique attack vector targeting operational agents; malicious web pages can inject instructions into an agent via visual elements or hidden text, and how to distinguish real instructions from forged ones remains an open problem that has not been fully solved.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)