Verified75% confidenceFactExact time
Indirect Prompt Injection is the most harmful variant of Prompt Injection, where an attacker plants hidden instructions on a public page to have an agent execute them.
5
Sources
75%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
VerifiedPrompt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76% similarVerifiedIndirect injection refers to attackers hiding malicious instructions in external content that the model will read, such as webpage body text, email body text, or document content.76% similarUnverified间接提示注入（Indirect Prompt Injection）是重大威胁，要求 WebMCP 在协议层面将工具描述与页面内容严格隔离76% 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.74% similarUnverifiedPrompt注入攻击是当前Agent安全领域最受关注的威胁之一73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/552274API
curl https://kongchang.com/api/v1/knowledge/claims/552274MCP
get_claim(id=552274)