Log in Start free

Vulnerability · Published Nov 5, 2026 · Assigned by GitHub_M

CVE-2026-54142OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval

High 8.7

In plain English

A high-severity security flaw in openhuman from tinyhumansai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 45% of all known vulnerabilities).

Severity (CVSS 3.1)8.7High
Exploit odds (30 days)0.5%top 55.4% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

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.

Affected products (as reported)

VendorProductVersions
tinyhumansai openhuman < 0.57.13

Weakness: CWE-1427 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:N

References