Skip to main content
VulnerabilityPublished

CVE-2026-54142: tinyhumansai openhuman · Improper Neutralization of Input Used for LLM Prompting

Affects tinyhumansai openhumanSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 8.7 High : upgrade to 0.57.13 soon.

Data as of 5 Nov 2026, 16:49 UTC

CVSS 3.1 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (GitHub_M)CVSS 3.18.7
Patch
Available – fixed in 0.57.13
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 5 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 5 Nov 2026.

What to do

Upgrade tinyhumansai openhuman to 0.57.13.

Affected software

ProductAffectedFixed in
tinyhumansaiopenhumanAffected
  • <0.57.13
Fixed in
  • 0.57.13

AI-suggested

Upgrade OpenHuman to version 0.57.13 or later, where this vulnerability is fixed. No other mitigation is required as the fix neutralizes the embedded instructions in external content before processing. Users should ensure all connected integrations are updated accordingly.

Description

CVE-2026-54142 is a vulnerability in tinyhumansai's OpenHuman agent harness before version 0.57.13. It involves improper neutralization of input used for large language model (LLM) prompting during background synchronization of connected services like email, Slack, and Notion. This flaw allows attacker-controlled content to influence autonomous background agents to perform unauthorized actions without user approval. The vulnerability is fixed in version 0.57.13.

References

Community reviews

Loading reviews…