Skip to content
Fencer Intel
high 8.7

CVE-2026-54142 json

OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval

published last mo. modified 5d ago also EUVD-2026-117597 , GHSA-p9gw-q7cf-57qr

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository tinyhumansai/openhuman. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
8.7
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 44%
public exploits
0
none known

Summary

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13.

Patch / fix

Is CVE-2026-54142 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
6d ago

Exploit prediction

0.52% chance of exploitation in the next 30 days, higher than 44% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-p9gw-q7cf-57qr referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.7 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N

Affected products

  • tinyhumansai openhuman

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of tinyhumansai/openhuman published their own advisory on GitHub. Reviewed sources take precedence over it.