NetSight
high8.3

CVE-2026-54140

OpenHuman is an open-source agent harness available as a desktop application and Rust library.

Impact

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13.

An attacker can exploit this over the network, without logging in, but a user has to do something, such as open a file or a link. Specific conditions have to be met, which makes an attack harder. If it succeeds: high risk of data being read, high risk of data or systems being changed, high risk of outages. The attack can reach beyond the vulnerable component itself.

Affected products · Tinyhumansai

ProductAffected versions
OpenHuman
before 0.57.13
Version < 0.57.13

Weakness classification

References