Unverified50% confidenceFactExact time
AI assistants index and retrieve content based on user permissions, and permission leakage directly amplifies the risk of information disclosure.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen an AI customer service agent has execution permissions such as querying databases, calling APIs, and triggering workflows, the security risks of prompt injection are significantly amplified78% similarVerifiedWhen an AI system processes user input, it runs multiple safety classifiers in parallel to identify potentially harmful content.77% similarUnverified凡是具备外部内容读取能力同时又拥有账户操作权限的AI系统，都处于潜在的提示注入攻击面之中77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978108API
curl https://kongchang.com/api/v1/knowledge/claims/978108MCP
get_claim(id=978108)