---
id: CVE-2026-54142
title: >-
  OpenHuman: Indirect prompt injection via background email sync executes
  Composio actions without user approval
summary: >-
  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 place…
severity: high
cvss: 8.7
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N'
cvssSource: cna
cwe:
  - CWE-1427
vendor: tinyhumansai
product: openhuman
affected:
  - openhuman < 0.57.13
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: total
  timestamp: '2026-11-05T18:24:02.444218Z'
exploitAvailable: true
published: '2026-11-05'
updated: '2026-11-05'
sourceUpdated: '2026-11-05T18:24:38.878Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-54142'
references:
  - url: >-
      https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr
    label: >-
      https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr
  - url: 'https://github.com/tinyhumansai/openhuman/pull/3227'
    label: 'https://github.com/tinyhumansai/openhuman/pull/3227'
  - url: >-
      https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca
    label: >-
      https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca
  - url: 'https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13'
    label: 'https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13'
tags:
  - cve.org
  - exploit-available
ingestedAt: '2026-11-05T22:38:31.468Z'
---

## Overview

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.

## Affected

- `openhuman < 0.57.13`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.