Unverified50% confidenceCautionExact time
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
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIndirect 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.76% similarUnverified网页端受CORS、内容安全策略CSP和WebAssembly沙盒等浏览器安全策略约束72% similarUnverifiedPrompt injection is one of the most serious security threats facing LLM applications, and its mechanism is analogous to SQL injection in traditional web security.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.70% 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68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/813710API
curl https://kongchang.com/api/v1/knowledge/claims/813710MCP
get_claim(id=813710)