Answer in brief
CVE-2026-54140 records a High severity (CVSS 8.3) vulnerability in OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization. The current sources do not mark it as known exploited. The current feed maps tinyhumansai/openhuman (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.3. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps tinyhumansai/openhuman (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| tinyhumansai/openhumangeneric | <0.57.13 | 0.57.13 |
Published upstream
Nov 5, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Nov 5, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Nov 5, 2026
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.
Quoted source text, attributed separately from HOL analysis.