CVE-2026-54142

OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval

Published Nov 5, 2026 CVSS 3.1 · 8.7 High EPSS < 1% KEV · Not listed
Description
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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Tinyhumansai
Tinyhumansai openhuman
Vendors & Products Tinyhumansai
Tinyhumansai openhuman
Type Values Removed Values Added
Description 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.
Title OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval
Weaknesses CWE-1427
References
Metrics cvssV3_1

{'score': 8.7, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Nov 5, 2026, 6:24 PM
Reserved
Jun 11, 2026, 9:15 PM
Status
Deferred
Published
Nov 5, 2026, 5:18 PM
Modified
Nov 6, 2026, 9:32 PM