Unverified60% confidenceFactTime unknown
Relay service operators are technically capable of reading all request content, including prompts and model responses, posing data security risks.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified使用中转站时所有请求均经过中转站服务器，平台在技术上具备记录和审查用户输入输出内容的能力74% similarUnverifiedDial has a built-in inbound verification code reading capability that can automatically parse received SMS verification codes and feed them back into the agent workflow.73% similarUnverifiedA secure customer service Agent architecture is to have the model responsible only for classification and drafting, with all proposed replies or actions entering an approval queue to be truly executed only after human confirmation.69% similarUnverifiedIndirect prompt injection refers to a skill instructing the model to read a document from the web while malicious instructions are hidden in that document, potentially causing the model to treat external content as a trusted instruction source when processing it.68% similarUnverifiedCustomer messages should be treated as task data rather than as authorization to modify workflows; this is a direct defense against prompt injection attacks.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/25618API
curl https://kongchang.com/api/v1/knowledge/claims/25618MCP
get_claim(id=25618)