# CVE-2026-54142: OpenHuman prompt injection in background synchronization

Source: https://junglewise.ai/threats/cve-2026-54142-openhuman-is-an-open-source-agent-harness-available-as-a-desktop  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-11-05. Updated: 2026-11-05  
License: CC BY 4.0 with a link back

CVE-2026-54142 · Severity: high · CVSS 8.7 · Published 2026-11-05

OpenHuman is an open-source agent harness that integrates with external services like email, Slack, and Notion. Before version 0.57.13, attackers could inject malicious instructions into content from these services, which would be processed by background agents without proper validation. This could allow an attacker to manipulate the agent into sending messages, modifying files, or disclosing sensitive information without user approval.

Technologies: [Tinyhumans OpenHuman](https://junglewise.ai/threats/technologies/tinyhumans-openhuman). Vendors: [Tinyhumans](https://junglewise.ai/threats/vendors/tinyhumans).

## Quick answers

**Is CVE-2026-54142 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-54142 being exploited in the wild.

**How severe is CVE-2026-54142?** High severity, with a CVSS score of 8.7, published 5 November 2026.

**Which products and versions are affected?** Tinyhumans OpenHuman before 0.57.13.

**Is there a fix for CVE-2026-54142?** Yes: fixed in 0.57.13. Until then: Restrict or disable integrations with external services (email, Slack, Notion) until upgrading to version 0.57.13, or ensure background synchronization is disabled in settings. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-54142 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-54142?** Check whether you run Tinyhumans OpenHuman at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- Fixed in 0.57.13

Restrict or disable integrations with external services (email, Slack, Notion) until upgrading to version 0.57.13, or ensure background synchronization is disabled in settings.

## Technical details

The vulnerability stems from OpenHuman storing raw external content from connected services during background synchronization and inserting it into the model context without sanitization. The ApprovalGate system incorrectly treated background automation (lacking interactive chat context) as pre-authorized, allowing external-effect tool calls to execute without approval. An attacker with access to a connected account could deliver prompt-injection payloads that the LLM would interpret as commands to invoke Composio actions (send emails, post messages, modify content).

## Affected products

- TinyHumans OpenHuman before 0.57.13

## Timeline

- 2026-11-05: disclosed

## References

- [https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca](https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca)
- [https://github.com/tinyhumansai/openhuman/pull/3227](https://github.com/tinyhumansai/openhuman/pull/3227)

## Related threats

- [OpenHuman credential exposure through approval session identifier](https://junglewise.ai/threats/cve-2026-54145-openhuman-is-an-open-source-agent-harness-available-as-a-desktop)
- [OpenHuman remote code execution via unapproved Yuanbao channel messages](https://junglewise.ai/threats/cve-2026-54141-openhuman-is-an-open-source-agent-harness-available-as-a-desktop)
- [OpenHuman prompt injection via MCP server tool descriptions](https://junglewise.ai/threats/cve-2026-54140-openhuman-is-an-open-source-agent-harness-available-as-a-desktop)