mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-09-02 12:01:14 +00:00
37429e8a3e
`/c/new?prompt=…&submit=true` previously auto-submitted the prompt unconditionally. For deployments where users may receive crafted links from external sources, an authenticated victim's click can trigger an immediate, attacker-controlled prompt against a memory- or tool-enabled model — providing a 1-click vector for prompt-injection exfiltration via markdown image rendering. Add `interface.autoSubmitFromUrl` (default `true` to preserve current behavior). Operators handling sensitive memory/tool data can set it to `false` so URL-supplied prompts only pre-fill the composer; the user must press Send explicitly. |
||
|---|---|---|
| .. | ||
| api | ||
| client | ||
| data-provider | ||
| data-schemas | ||