Unverified50% confidenceTradeoffExact time
Connecting an LLM to the local file system and active browser sessions means that every prompt injection attack could potentially evolve into an actual exploit of the local system.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该漏洞与供应链攻击结合后，攻击者只需在热门开源包中夹带伪装的git.exe，便可在全球数以万计的Cursor用户机器上无声触发执行67% similarUnverifiedDuring installation, the Kuaima client needs to modify system network configurations and Cursor's internal files, and such behavior is easily flagged as malicious by the active defense mechanisms of security software67% similarUnverifiedQR code access carries security risks including replay attacks, session credential leakage due to long-lived tokens, and man-in-the-middle attacks.64% similarUnverifiedDependency confusion attacks exploit the characteristic of package managers to check public sources first when resolving dependencies, allowing attackers to register package names used internally by enterprises in order to trick build systems into downloading malicious code.64% similarUnverifiedLLMs are vulnerable to prompt injection attacks, where malicious web pages or files can embed hidden instructions to induce AI to perform unintended actions.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/896858API
curl https://kongchang.com/api/v1/knowledge/claims/896858MCP
get_claim(id=896858)