Unverified50% confidenceFactExact time
Attacks targeting protocol intent rather than protocol implementation are referred to in academia as Semantic Attacks.
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA social engineering attack is an attack method in which the attacker obtains sensitive information or system access through psychological manipulation rather than technical means.71% similarVerifiedPrompt injection attacks induce AI agents to execute malicious operations by embedding text disguised as system instructions in code comments, documentation, web content, or even file names.71% similarVerifiedPrompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束70% similarVerifiedIndirect prompt injection attacks plant hidden instructions within normal business data to induce Agents into executing unauthorized operations, representing a security risk at the semantic level rather than the code level.70% similarUnverifiedAnthropic's cybersecurity safeguards target scenarios involving the prevention of models being misused to generate malicious code, plan attack vectors, or assist in launching cyberattacks against critical infrastructure.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/965362API
curl https://kongchang.com/api/v1/knowledge/claims/965362MCP
get_claim(id=965362)