Verified80% confidenceFactExact time
In a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.
6
Sources
80%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
Related Claims
Unverified提示注入攻击（Prompt Injection）指恶意第三方在Agent处理的内容中嵌入指令，劫持Agent的行为意图81% 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78% similarUnverifiedAgents may execute destructive operations far beyond what was intended due to hallucination or prompt injection attacks.76% similarUnverifiedAttackers may circumvent AI safety restrictions through jailbreak prompts, decomposing tasks step by step, or using the model for peripheral auxiliary work.73% similarVerifiedPrompt injection attacks are a serious threat facing local AI Agents, as maliciously crafted content in files processed by the Agent may induce it to execute dangerous operations.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/112620API
curl https://kongchang.com/api/v1/knowledge/claims/112620MCP
get_claim(id=112620)