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.
Written by anthropic/claude-haiku-5.5 from the sources below. Verify against them.
- Exploited
- No known exploitation
- Fix
- Fixed in 0.57.13
- Who is exposed
- Default setups
Do first: Check every install: default setups are affected.
- Last modified
- A 0-100 score for how much a CVE matters across the industry: exploitation, exposure, how widely the software is used, severity and whether a fix exists.What do these mean? →
- 31/100 · provisional
- How many real-world setups can hit the bug, from the vendor's advisory and CISA data. It does not know your setup.What do these mean? →
- Default setups
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
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.
Read the original 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.
cve.now Index
- Exploitation?/40Unknown. No CISA SSVC exploitation rating yet
- Exposure22/25Default setups, reachable over the network without a login
- Reach?/20Unknown. No tracked technology or package matched
- Severity9/10CVSS 9.0
- No patch0/5No signal
What would change the score
- Would score about 71 if added to CISA KEV
- Would score about 66 if CISA's SSVC rates exploitation active
What to do
Check every install: default setups are affected.
Upgrade to a fixed version: 0.57.13.
Timeline
- CVE published
- First seen by cve.now
- Posted on X by cve.now
Affected versions
- tinyhumansai openhuman
fixed in 0.57.13
Evidence 4
- Advisory
- Repository
- Repository
- Repository
Corrections
None so far.
Something wrong on this page? Report an error. Every fix is listed here.
Questions about CVE-2026-54141
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: cve.now feed data
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: github.com
Which versions are affected by CVE-2026-54141?
openhuman: before 0.57.13.Source: cve.now feed data
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: github.com
How do I fix CVE-2026-54141?
Upgrade OpenHuman to 0.57.13 or later, which contains the fix.Source: github.com