Unverified50% confidenceFactExact time
Social engineering attacks refer to attacks in which the attacker uses psychological manipulation rather than technical means to deceive targets in order to obtain sensitive information or access.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAttackers are attempting to build automated attack workflows capable of autonomously executing multi-step tasks such as reconnaissance, infiltration, and social engineering75% 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.67% similarUnverified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64% similarUnverifiedAnthropic has established proactive threat intelligence capabilities, anticipating new types of attacks before they emerge at scale by analyzing misuse patterns and tracking the evolution of attack techniques64% similarUnverified环境注入是Agent因具备环境交互能力而特有的新型攻击面，攻击者将恶意指令嵌入Agent读取的外部内容中触发执行64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/943748API
curl https://kongchang.com/api/v1/knowledge/claims/943748MCP
get_claim(id=943748)