Skip to content
High 8.7

OpenHumanにメール同期経由で外部操作を実行される脆弱性

CVE-2026-54142 First seen on SecPulse

Summary

OpenHumanでは、連携したメールやSlackの内容に埋め込まれた指示によって、利用者の承認を経ずにComposioの操作が実行される脆弱性が公表されました。影響を受けるのは0.57.13より前のバージョンで、0.57.13で修正されています。連携サービスを使っている場合は、早めに0.57.13以上へ更新してください。

AI summary

Produced by SecPulse using an external AI model; it may contain mistakes. Check the original description and references below before acting on it.

OpenHumanでは、連携したメールやSlackの内容に埋め込まれた指示によって、利用者の承認を経ずにComposioの操作が実行される脆弱性が公表されました。影響を受けるのは0.57.13より前のバージョンで、0.57.13で修正されています。連携サービスを使っている場合は、早めに0.57.13以上へ更新してください。

Original description The description as published by the source.

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13.

Source: CVE.org (CVE Program・cvelistV5) NVD GitHub Advisory

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details