---
id: "CVE-2026-54142"
kind: "vulnerability"
aliases: ["CVE-2026-54142"]
title: "OpenHuman: prompt injection from connected email and Slack triggers unapproved actions"
severity: "high"
cvss: 8.7
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-agents", "ai-tooling", "composio", "email-integration", "notion-integration", "openhuman", "slack-integration"]
not_affected_if: ["interactive-chat-only", "no-active-integrations"]
published_at: "2026-11-05T17:18:19+00:00"
first_seen_at: "2026-11-05T17:40:04+00:00"
updated_at: "2026-11-05T17:42:09+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-54142", "first_seen_at": "2026-11-05T17:40:04+00:00"}]
exploit_sources: []
---

# OpenHuman: prompt injection from connected email and Slack triggers unapproved actions

OpenHuman is an open-source agent harness that runs background sync for services like email, Slack and Notion. Before 0.57.13, content from those services reaches the model unfiltered, so embedded instructions can make the agent call Composio actions without an approval prompt, letting an attacker send messages, forward data or read memory and integrations.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed OpenHuman version against `0.57.13`
- Look for active background sync integrations (email, Slack, Notion) connected to OpenHuman
- Review whether tool calls run without an interactive chat context

## Fix

- OpenHuman: move to `0.57.13` or later

## Timeline

- 2026-11-05T17:40:04+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-54142

## Documents

- [advisory] Vendor advisory: github.com https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr
- [fix] Patch: github.com https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca
- [fix] Release notes: github.com https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13

## From the sources

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.

---

_Free to read, with fair use of about 60 pages a minute. For higher limits or API access: sales@infrastack.ai_