CVE-2026-54142
Published:November 05, 2026
Updated:November 12, 2026
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 Packages
https://github.com/tinyhumansai/openhuman.git (GITHUB):
Affected version(s) >=v0.52.6 <v0.57.13Fix Suggestion:
Update to version v0.57.13Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
9.4
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
NONE
Subsequent System Confidentiality
HIGH
Subsequent System Integrity
HIGH
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.7
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
NONE
Scope
CHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
NONE
Weakness Type (CWE)
Improper Neutralization of Input Used for LLM Prompting
EPSS
Base Score:
0.52